Deep learning-assisted ultra-fast/low-dose whole-body PET/CT imaging

Revolutionizing tumor detection and classification in multimodality imaging based on deep learning approaches: methods, applications and limitations

BACKGROUND

The emergence of deep learning (DL) techniques has revolutionized tumor detection and classification in medical imaging, with multimodal medical imaging (MMI) gaining recognition for its precision in diagnosis, treatment, and progression tracking.

OBJECTIVE

This review comprehensively examines DL methods in transforming tumor detection and classification across MMI modalities, aiming to provide insights into advancements, limitations, and key challenges for further progress.

METHODS

Systematic literature analysis identifies DL studies for tumor detection and classification, outlining methodologies including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and their variants. Integration of multimodality imaging enhances accuracy and robustness.

RESULTS

Recent advancements in DL-based MMI evaluation methods are surveyed, focusing on tumor detection and classification tasks. Various DL approaches, including CNNs, YOLO, Siamese Networks, Fusion-Based Models, Attention-Based Models, and Generative Adversarial Networks, are discussed with emphasis on PET-MRI, PET-CT, and SPECT-CT.

FUTURE DIRECTIONS

The review outlines emerging trends and future directions in DL-based tumor analysis, aiming to guide researchers and clinicians toward more effective diagnosis and prognosis. Continued innovation and collaboration are stressed in this rapidly evolving domain.

CONCLUSION

Conclusions drawn from literature analysis underscore the efficacy of DL approaches in tumor detection and classification, highlighting their potential to address challenges in MMI analysis and their implications for clinical practice.

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

PURPOSE

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.

METHODS

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.

RESULTS

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 ± 0.824 dB, 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 ± 0.801 dB, 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.

CONCLUSIONS

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.

Deep learning-based PET image denoising and reconstruction: a review

This review focuses on positron emission tomography (PET) imaging algorithms and traces the evolution of PET image reconstruction methods. First, we provide an overview of conventional PET image reconstruction methods from filtered backprojection through to recent iterative PET image reconstruction algorithms, and then review deep learning methods for PET data up to the latest innovations within three main categories. The first category involves post-processing methods for PET image denoising. The second category comprises direct image reconstruction methods that learn mappings from sinograms to the reconstructed images in an end-to-end manner. The third category comprises iterative reconstruction methods that combine conventional iterative image reconstruction with neural-network enhancement. We discuss future perspectives on PET imaging and deep learning technology.

Intelligent ultrafast total-body PET for sedation-free pediatric [18F]FDG imaging

PURPOSE

This study aims to develop deep learning techniques on total-body PET to bolster the feasibility of sedation-free pediatric PET imaging.

METHODS

A deformable 3D U-Net was developed based on 245 adult subjects with standard total-body PET imaging for the quality enhancement of simulated rapid imaging. The developed method was first tested on 16 children receiving total-body [18F]FDG PET scans with standard 300-s acquisition time with sedation. Sixteen rapid scans (acquisition time about 3 s, 6 s, 15 s, 30 s, and 75 s) were retrospectively simulated by selecting the reconstruction time window. In the end, the developed methodology was prospectively tested on five children without sedation to prove the routine feasibility.

RESULTS

The approach significantly improved the subjective image quality and lesion conspicuity in abdominal and pelvic regions of the generated 6-s data. In the first test set, the proposed method enhanced the objective image quality metrics of 6-s data, such as PSNR (from 29.13 to 37.09, p < 0.01) and SSIM (from 0.906 to 0.921, p < 0.01). Furthermore, the errors of mean standardized uptake values (SUVmean) for lesions between 300-s data and 6-s data were reduced from 12.9 to 4.1% (p < 0.01), and the errors of max SUV (SUVmax) were reduced from 17.4 to 6.2% (p < 0.01). In the prospective test, radiologists reached a high degree of consistency on the clinical feasibility of the enhanced PET images.

CONCLUSION

The proposed method can effectively enhance the image quality of total-body PET scanning with ultrafast acquisition time, leading to meeting clinical diagnostic requirements of lesion detectability and quantification in abdominal and pelvic regions. It has much potential to solve the dilemma of the use of sedation and long acquisition time that influence the health of pediatric patients.

A Review on Low-Dose Emission Tomography Post-Reconstruction Denoising with Neural Network Approaches

Low-dose emission tomography (ET) plays a crucial role in medical imaging, enabling the acquisition of functional information for various biological processes while minimizing the patient dose. However, the inherent randomness in the photon counting process is a source of noise which is amplified in low-dose ET. This review article provides an overview of existing post-processing techniques, with an emphasis on deep neural network (NN) approaches. Furthermore, we explore future directions in the field of NN-based low-dose ET. This comprehensive examination sheds light on the potential of deep learning in enhancing the quality and resolution of low-dose ET images, ultimately advancing the field of medical imaging.

Investigation of PET image quality with acquisition time/bed and enhancement of lesion quantification accuracy through deep progressive learning

OBJECTIVE

To improve the PET image quality by a deep progressive learning (DPL) reconstruction algorithm and evaluate the DPL performance in lesion quantification.

METHODS

We reconstructed PET images from 48 oncological patients using ordered subset expectation maximization (OSEM) and deep progressive learning (DPL) methods. The patients were enrolled into three overlapped studies: 11 patients for image quality assessment (study 1), 34 patients for sub-centimeter lesion quantification (study 2), and 28 patients for imaging of overweight or obese individuals (study 3). In study 1, we evaluated the image quality visually based on four criteria: overall score, image sharpness, image noise, and diagnostic confidence. We also measured the image quality quantitatively using the signal-to-background ratio (SBR), signal-to-noise ratio (SNR), contrast-to-background ratio (CBR), and contrast-to-noise ratio (CNR). To evaluate the performance of the DPL algorithm in quantifying lesions, we compared the maximum standardized uptake values (SUVmax), SBR, CBR, SNR and CNR of 63 sub-centimeter lesions in study 2 and 44 lesions in study 3.

RESULTS

DPL produced better PET image quality than OSEM did based on the visual evaluation methods when the acquisition time was 0.5, 1.0 and 1.5 min/bed. However, no discernible differences were found between the two methods when the acquisition time was 2.0, 2.5 and 3.0 min/bed. Quantitative results showed that DPL had significantly higher values of SBR, CBR, SNR, and CNR than OSEM did for each acquisition time. For sub-centimeter lesion quantification, the SUVmax, SBR, CBR, SNR, and CNR of DPL were significantly enhanced, compared with OSEM. Similarly, for lesion quantification in overweight and obese patients, DPL significantly increased these parameters compared with OSEM.

CONCLUSION

The DPL algorithm dramatically enhanced the quality of PET images and enabled more accurate quantification of sub-centimeters lesions in patients and lesions in overweight or obese patients. This is particularly beneficial for overweight or obese patients who usually have lower image quality due to the increased attenuation.

Low 18F-fluorodeoxyglucose dose positron emission tomography assisted by a deep-learning image-denoising technique in patients with lymphoma

Background

Patients with lymphoma receive multiple positron emission tomography/computed tomography (PET/CT) exams for monitoring of the therapeutic response. With PET imaging, a reduced level of injected fluorine-18 fluorodeoxyglucose ([18F]FDG) activity can be administered while maintaining the image quality. In this study, we investigated the efficacy of applying a deep learning (DL) denoising-technique on image quality and the quantification of metabolic parameters and Deauville score (DS) of a low [18F]FDG dose PET in patients with lymphoma.

Methods

This study retrospectively enrolled 62 patients who underwent [18F]FDG PET scans. The low-dose (LD) data were simulated by taking a 50% duration of routine-dose (RD) PET list-mode data in the reconstruction, and a U-Net-based denoising neural network was applied to improve the images of LD PET. The visual image quality score (1 = undiagnostic, 5 = excellent) and DS were assessed in all patients by nuclear radiologists. The maximum, mean, and standard deviation (SD) of the standardized uptake value (SUV) in the liver and mediastinum were measured. In addition, lesions in some patients were segmented using a fixed threshold of 2.5, and their SUV, metabolic tumor volume (MTV), and tumor lesion glycolysis (TLG) were measured. The correlation coefficient and limits of agreement between the RD and LD group were analyzed.

Results

The visual image quality of the LD group was improved compared with the RD group. The DS was similar between the RD and LD group, and the negative (DS 1-3) and positive (DS 4-5) results remained unchanged. The correlation coefficients of SUV in the liver, mediastinum, and lesions were all >0.85. The mean differences of SUVmax and SUVmean between the RD and LD groups, respectively, were 0.22 [95% confidence interval (CI): -0.19 to 0.64] and 0.02 (95% CI: -0.17 to 0.20) in the liver, 0.13 (95% CI: -0.17 to 0.42) and 0.02 (95% CI: -0.12 to 0.16) in the mediastinum, and -0.75 (95% CI: -3.42 to 1.91), and -0.13 (95% CI: -0.57 to 0.31) in lesions. The mean differences in MTV and TLG were 0.85 (95% CI: -2.27 to 3.98) and 4.06 (95% CI: -20.53 to 28.64) between the RD and LD groups.

Conclusions

The DL denoising technique enables accurate tumor assessment and quantification with LD [18F]FDG PET imaging in patients with lymphoma.

Reducing pediatric total-body PET/CT imaging scan time with multimodal artificial intelligence technology

OBJECTIVES

This study aims to decrease the scan time and enhance image quality in pediatric total-body PET imaging by utilizing multimodal artificial intelligence techniques.

METHODS

A total of 270 pediatric patients who underwent total-body PET/CT scans with a uEXPLORER at the Sun Yat-sen University Cancer Center were retrospectively enrolled. 18F-fluorodeoxyglucose (18F-FDG) was administered at a dose of 3.7 MBq/kg with an acquisition time of 600 s. Short-term scan PET images (acquired within 6, 15, 30, 60 and 150 s) were obtained by truncating the list-mode data. A three-dimensional (3D) neural network was developed with a residual network as the basic structure, fusing low-dose CT images as prior information, which were fed to the network at different scales. The short-term PET images and low-dose CT images were processed by the multimodal 3D network to generate full-length, high-dose PET images. The nonlocal means method and the same 3D network without the fused CT information were used as reference methods. The performance of the network model was evaluated by quantitative and qualitative analyses.

RESULTS

Multimodal artificial intelligence techniques can significantly improve PET image quality. When fused with prior CT information, the anatomical information of the images was enhanced, and 60 s of scan data produced images of quality comparable to that of the full-time data.

CONCLUSION

Multimodal artificial intelligence techniques can effectively improve the quality of pediatric total-body PET/CT images acquired using ultrashort scan times. This has the potential to decrease the use of sedation, enhance guardian confidence, and reduce the probability of motion artifacts.

Utilizing deep learning techniques to improve image quality and noise reduction in preclinical low-dose PET images in the sinogram domain

BACKGROUND

Low-dose positron emission tomography (LD-PET) imaging is commonly employed in preclinical research to minimize radiation exposure to animal subjects. However, LD-PET images often exhibit poor quality and high noise levels due to the low signal-to-noise ratio. Deep learning (DL) techniques such as generative adversarial networks (GANs) and convolutional neural network (CNN) have the capability to enhance the quality of images derived from noisy or low-quality PET data, which encodes critical information about radioactivity distribution in the body.

PURPOSE

Our objective was to optimize the image quality and reduce noise in preclinical PET images by utilizing the sinogram domain as input for DL models, resulting in improved image quality as compared to LD-PET images.

METHODS

A GAN and CNN model were utilized to predict high-dose (HD) preclinical PET sinograms from the corresponding LD preclinical PET sinograms. In order to generate the datasets, experiments were conducted on micro-phantoms, animal subjects (rats), and virtual simulations. The quality of DL-generated images was weighted by performing the following quantitative measures: structural similarity index measure (SSIM), root mean squared error (RMSE), peak signal-to-noise ratio (PSNR), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). Additionally, DL input and output were both subjected to a spatial resolution calculation of full width half maximum (FWHM) and full width tenth maximum (FWTM). DL outcomes were then compared with the conventional denoising algorithms such as non-local means (NLM), block-matching, and 3D filtering (BM3D).

RESULTS

The DL models effectively learned image features and produced high-quality images, as reflected in the quantitative metrics. Notably, the FWHM and FWTM values of DL PET images exhibited significantly improved accuracy compared to LD, NLM, and BM3D PET images, and just as precise as HD PET images. The MSE loss underscored the excellent performance of the models, indicating that the models performed well. To further improve the training, the generator loss (G loss) was increased to a value higher than the discriminator loss (D loss), thereby achieving convergence in the GAN model.

CONCLUSIONS

The sinograms generated by the GAN network closely resembled real HD preclinical PET sinograms and were more realistic than LD. There was a noticeable improvement in image quality and noise factor in the predicted HD images. Importantly, DL networks did not fully compromise the spatial resolution of the images.

PET image denoising based on denoising diffusion probabilistic model

PURPOSE

Due to various physical degradation factors and limited counts received, PET image quality needs further improvements. The denoising diffusion probabilistic model (DDPM) was a distribution learning-based model, which tried to transform a normal distribution into a specific data distribution based on iterative refinements. In this work, we proposed and evaluated different DDPM-based methods for PET image denoising.

METHODS

Under the DDPM framework, one way to perform PET image denoising was to provide the PET image and/or the prior image as the input. Another way was to supply the prior image as the network input with the PET image included in the refinement steps, which could fit for scenarios of different noise levels. 150 brain [[Formula: see text]F]FDG datasets and 140 brain [[Formula: see text]F]MK-6240 (imaging neurofibrillary tangles deposition) datasets were utilized to evaluate the proposed DDPM-based methods.

RESULTS

Quantification showed that the DDPM-based frameworks with PET information included generated better results than the nonlocal mean, Unet and generative adversarial network (GAN)-based denoising methods. Adding additional MR prior in the model helped achieved better performance and further reduced the uncertainty during image denoising. Solely relying on MR prior while ignoring the PET information resulted in large bias. Regional and surface quantification showed that employing MR prior as the network input while embedding PET image as a data-consistency constraint during inference achieved the best performance.

CONCLUSION

DDPM-based PET image denoising is a flexible framework, which can efficiently utilize prior information and achieve better performance than the nonlocal mean, Unet and GAN-based denoising methods.

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

PURPOSE

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.

METHODS

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.

RESULTS

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 ± 5.45 dB (p < 0.05), 33.77 ± 6.18 dB (p < 0.05), and 38.58 ± 7.28 dB (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.

CONCLUSION

The findings demonstrate the potential of the proposed technique for improving the image quality of a PET scanner with a 320 mm 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.

Image reconstruction using UNET-transformer network for fast and low-dose PET scans

INTRODUCTION

Low-dose and fast PET imaging (low-count PET) play a significant role in enhancing patient safety, healthcare efficiency, and patient comfort during medical imaging procedures. To achieve high-quality images with low-count PET scans, effective reconstruction models are crucial for denoising and enhancing image quality. The main goal of this paper is to develop an effective and accurate deep learning-based method for reconstructing low-count PET images, which is a challenging problem due to the limited amount of available data and the high level of noise in the acquired images. The proposed method aims to improve the quality of reconstructed PET images while preserving important features, such as edges and small details, by combining the strengths of UNET and Transformer networks.

MATERIAL AND METHODS

The proposed TrUNET-MAPEM model integrates a residual UNET-transformer regularizer into the unrolled maximum a posteriori expectation maximization (MAPEM) algorithm for PET image reconstruction. A loss function based on a combination of structural similarity index (SSIM) and mean squared error (MSE) is utilized to evaluate the accuracy of the reconstructed images. The simulated dataset was generated using the Brainweb phantom, while the real patient dataset was acquired using a Siemens Biograph mMR PET scanner. We also implemented state-of-the-art methods for comparison purposes: OSEM, MAPOSEM, and supervised learning using 3D-UNET network. The reconstructed images are compared to ground truth images using metrics such as peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and relative root mean square error (rRMSE) to quantitatively evaluate the accuracy of the reconstructed images.

RESULTS

Our proposed TrUNET-MAPEM approach was evaluated using both simulated and real patient data. For the patient data, our model achieved an average PSNR of 33.72 dB, an average SSIM of 0.955, and an average rRMSE of 0.39. These results outperformed other methods which had average PSNRs of 36.89 dB, 34.12 dB, and 33.52 db, average SSIMs of 0.944, 0.947, and 0.951, and average rRMSEs of 0.59, 0.49, and 0.42. For the simulated data, our model achieved an average PSNR of 31.23 dB, an average SSIM of 0.95, and an average rRMSE of 0.55. These results also outperformed other state-of-the-art methods, such as OSEM, MAPOSEM, and 3DUNET-MAPEM. The model demonstrates the potential for clinical use by successfully reconstructing smooth images while preserving edges. The comparison with other methods demonstrates the superiority of our approach, as it outperforms all other methods for all three metrics.

CONCLUSION

The proposed TrUNET-MAPEM model presents a significant advancement in the field of low-count PET image reconstruction. The results demonstrate the potential for clinical use, as the model can produce images with reduced noise levels and better edge preservation compared to other reconstruction and post-processing algorithms. The proposed approach may have important clinical applications in the early detection and diagnosis of various diseases.

Applications of machine learning and deep learning in SPECT and PET imaging: General overview, challenges and future prospects

The integration of positron emission tomography (PET) and single-photon emission computed tomography (SPECT) imaging techniques with machine learning (ML) algorithms, including deep learning (DL) models, is a promising approach. This integration enhances the precision and efficiency of current diagnostic and treatment strategies while offering invaluable insights into disease mechanisms. In this comprehensive review, we delve into the transformative impact of ML and DL in this domain. Firstly, a brief analysis is provided of how these algorithms have evolved and which are the most widely applied in this domain. Their different potential applications in nuclear imaging are then discussed, such as optimization of image adquisition or reconstruction, biomarkers identification, multimodal fusion and the development of diagnostic, prognostic, and disease progression evaluation systems. This is because they are able to analyse complex patterns and relationships within imaging data, as well as extracting quantitative and objective measures. Furthermore, we discuss the challenges in implementation, such as data standardization and limited sample sizes, and explore the clinical opportunities and future horizons, including data augmentation and explainable AI. Together, these factors are propelling the continuous advancement of more robust, transparent, and reliable systems.

Current and Future Use of Long Axial Field-of-View Positron Emission Tomography/Computed Tomography Scanners in Clinical Oncology

The latest technical development in the field of positron emission tomography/computed tomography (PET/CT) imaging has been the extension of the PET axial field-of-view. As a result of the increased number of detectors, the long axial field-of-view (LAFOV) PET systems are not only characterized by a larger anatomical coverage but also by a substantially improved sensitivity, compared with conventional short axial field-of-view PET systems. In clinical practice, this innovation has led to the following optimization: (1) improved overall image quality, (2) decreased duration of PET examinations, (3) decreased amount of radioactivity administered to the patient, or (4) a combination of any of the above. In this review, novel applications of LAFOV PET in oncology are highlighted and future directions are discussed.

Feasibility of a deep learning algorithm to achieve the low-dose 68Ga-FAPI/the fast-scan PET images: a multicenter study

OBJECTIVES

Our work aims to study the feasibility of a deep learning algorithm to reduce the 68Ga-FAPI radiotracer injected activity and/or shorten the scanning time and to investigate its effects on image quality and lesion detection ability.

METHODS

The data of 130 patients who underwent 68Ga-FAPI positron emission tomography (PET)/CT in two centers were studied. Predicted full-dose images (DL-22%, DL-28% and DL-33%) were obtained from three groups of low-dose images using a deep learning method and compared with the standard-dose images (raw data). Injection activity for full-dose images was 2.16 ± 0.61 MBq/kg. The quality of the predicted full-dose PET images was subjectively evaluated by two nuclear physicians using a 5-point Likert scale, and objectively evaluated by the peak signal-to-noise ratio, structural similarity index and root mean square error. The maximum standardized uptake value and the mean standardized uptake value (SUVmean) were used to quantitatively analyze the four volumes of interest (the brain, liver, left lung and right lung) and all lesions, and the lesion detection rate was calculated.

RESULTS

Data showed that the DL-33% images of the two test data sets met the clinical diagnosis requirements, and the overall lesion detection rate of the two centers reached 95.9%.

CONCLUSION

Through deep learning, we demonstrated that reducing the 68Ga-FAPI injected activity and/or shortening the scanning time in PET/CT imaging was feasible. In addition, 68Ga-FAPI dose as low as 33% of the standard dose maintained acceptable image quality.

ADVANCES IN KNOWLEDGE

This is the first study of low-dose 68Ga-FAPI PET images from two centers using a deep learning algorithm.

Enhanced PET imaging using progressive conditional deep image prior

Objective.Unsupervised learning-based methods have been proven to be an effective way to improve the image quality of positron emission tomography (PET) images when a large dataset is not available. However, when the gap between the input image and the target PET image is large, direct unsupervised learning can be challenging and easily lead to reduced lesion detectability. We aim to develop a new unsupervised learning method to improve lesion detectability in patient studies.Approach.We applied the deep progressive learning strategy to bridge the gap between the input image and the target image. The one-step unsupervised learning is decomposed into two unsupervised learning steps. The input image of the first network is an anatomical image and the input image of the second network is a PET image with a low noise level. The output of the first network is also used as the prior image to generate the target image of the second network by iterative reconstruction method.Results.The performance of the proposed method was evaluated through the phantom and patient studies and compared with non-deep learning, supervised learning and unsupervised learning methods. The results showed that the proposed method was superior to non-deep learning and unsupervised methods, and was comparable to the supervised method.Significance.A progressive unsupervised learning method was proposed, which can improve image noise performance and lesion detectability.

Employing Multiple Low-Dose PET Images (at Different Dose Levels) as Prior Knowledge to Predict Standard-Dose PET Images

The existing deep learning-based denoising methods predicting standard-dose PET images (S-PET) from the low-dose versions (L-PET) solely rely on a single-dose level of PET images as the input of deep learning network. In this work, we exploited the prior knowledge in the form of multiple low-dose levels of PET images to estimate the S-PET images. To this end, a high-resolution ResNet architecture was utilized to predict S-PET images from 6 to 4% L-PET images. For the 6% L-PET imaging, two models were developed; the first and second models were trained using a single input of 6% L-PET and three inputs of 6%, 4%, and 2% L-PET as input to predict S-PET images, respectively. Similarly, for 4% L-PET imaging, a model was trained using a single input of 4% low-dose data, and a three-channel model was developed getting 4%, 3%, and 2% L-PET images. The performance of the four models was evaluated using structural similarity index (SSI), peak signal-to-noise ratio (PSNR), and root mean square error (RMSE) within the entire head regions and malignant lesions. The 4% multi-input model led to improved SSI and PSNR and a significant decrease in RMSE by 22.22% and 25.42% within the entire head region and malignant lesions, respectively. Furthermore, the 4% multi-input network remarkably decreased the lesions' SUVmean bias and SUVmax bias by 64.58% and 37.12% comparing to single-input network. In addition, the 6% multi-input network decreased the RMSE within the entire head region, within the lesions, lesions' SUVmean bias, and SUVmax bias by 37.5%, 39.58%, 86.99%, and 45.60%, respectively. This study demonstrated the significant benefits of using prior knowledge in the form of multiple L-PET images to predict S-PET images.

Simultaneous quantitative imaging of two PET radiotracers via the detection of positron-electron annihilation and prompt gamma emissions

In conventional positron emission tomography (PET), only one radiotracer can be imaged at a time, because all PET isotopes produce the same two 511 keV annihilation photons. Here we describe an image reconstruction method for the simultaneous in vivo imaging of two PET tracers and thereby the independent quantification of two molecular signals. This method of multiplexed PET imaging leverages the 350-700 keV range to maximize the capture of 511 keV annihilation photons and prompt γ-ray emission in the same energy window, hence eliminating the need for energy discrimination during reconstruction or for signal separation beforehand. We used multiplexed PET to track, in mice with subcutaneous tumours, the biodistributions of intravenously injected [124I]I-trametinib and 2-deoxy-2-[18F]fluoro-D-glucose, [124I]I-trametinib and its nanoparticle carrier [89Zr]Zr-ferumoxytol, and the prostate-specific membrane antigen (PSMA) and infused PSMA-targeted chimaeric antigen receptor T cells after the systemic administration of [68Ga]Ga-PSMA-11 and [124I]I. Multiplexed PET provides more information depth, gives new uses to prompt γ-ray-emitting isotopes, reduces radiation burden by omitting the need for an additional computed-tomography scan and can be implemented on preclinical and clinical systems without any modifications in hardware or image acquisition software.

An Investigation of Lesion Detection Accuracy for Artificial Intelligence-Based Denoising of Low-Dose 64Cu-DOTATATE PET Imaging in Patients with Neuroendocrine Neoplasms

Frequent somatostatin receptor PET, for example, 64Cu-DOTATATE PET, is part of the diagnostic work-up of patients with neuroendocrine neoplasms (NENs), resulting in high accumulated radiation doses. Scan-related radiation exposure should be minimized in accordance with the as-low-as-reasonably achievable principle, for example, by reducing injected radiotracer activity. Previous investigations found that reducing 64Cu-DOTATATE activity to below 50 MBq results in inadequate image quality and lesion detection. We therefore investigated whether image quality and lesion detection of less than 50 MBq of 64Cu-DOTATATE PET could be restored using artificial intelligence (AI). Methods: We implemented a parameter-transferred Wasserstein generative adversarial network for patients with NENs on simulated low-dose 64Cu-DOTATATE PET images corresponding to 25% (PET25%), or about 48 MBq, of the injected activity of the reference full dose (PET100%), or about 191 MBq, to generate denoised PET images (PETAI). We included 38 patients in the training sets for network optimization. We analyzed PET intensity correlation, peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mean-square error (MSE) of PETAI/PET100% versus PET25%/PET100% Two readers assessed Likert scale-defined image quality (1, very poor; 2, poor; 3, moderate; 4, good; 5, excellent) and identified lesion-suspicious foci on PETAI and PET100% in a subset of the patients with no more than 20 lesions per organ (n = 33) to allow comparison of all foci on a 1:1 basis. Detected foci were scored (C1, definite lesion; C0, lesion-suspicious focus) and matched with PET100% as the reference. True-positive (TP), false-positive (FP), and false-negative (FN) lesions were assessed. Results: For PETAI/PET100% versus PET25%/PET100%, PET intensity correlation had a goodness-of-fit value of 0.94 versus 0.81, PSNR was 58.1 versus 53.0, SSIM was 0.908 versus 0.899, and MSE was 2.6 versus 4.7. Likert scale-defined image quality was rated good or excellent in 33 of 33 and 32 of 33 patients on PET100% and PETAI, respectively. Total number of detected lesions was 118 on PET100% and 115 on PETAI Only 78 PETAI lesions were TP, 40 were FN, and 37 were FP, yielding detection sensitivity (TP/(TP+FN)) and a false discovery rate (FP/(TP+FP)) of 66% (78/118) and 32% (37/115), respectively. In 62% (23/37) of cases, the FP lesion was scored C1, suggesting a definite lesion. Conclusion: PETAI improved visual similarity with PET100% compared with PET25%, and PETAI and PET100% had similar Likert scale-defined image quality. However, lesion detection analysis performed by physicians showed high proportions of FP and FN lesions on PETAI, highlighting the need for clinical validation of AI algorithms.

Imaging quality of an artificial intelligence denoising algorithm: validation in 68Ga PSMA-11 PET for patients with biochemical recurrence of prostate cancer

BACKGROUND

⁶⁸ Ga-PSMA PET is the leading prostate cancer imaging technique, but the image quality remains noisy and could be further improved using an artificial intelligence-based denoising algorithm. To address this issue, we analyzed the overall quality of reprocessed images compared to standard reconstructions. We also analyzed the diagnostic performances of the different sequences and the impact of the algorithm on lesion intensity and background measures.

METHODS

We retrospectively included 30 patients with biochemical recurrence of prostate cancer who had undergone ⁶⁸ Ga-PSMA-11 PET-CT. We simulated images produced using only a quarter, half, three-quarters, or all of the acquired data material reprocessed using the SubtlePET® denoising algorithm. Three physicians with different levels of experience blindly analyzed every sequence and then used a 5-level Likert scale to assess the series. The binary criterion of lesion detectability was compared between series. We also compared lesion SUV, background uptake, and diagnostic performances of the series (sensitivity, specificity, accuracy).

RESULTS

VPFX-derived series were classified differently but better than standard reconstructions (p < 0.001) using half the data. Q.Clear series were not classified differently using half the signal. Some series were noisy but had no significant effect on lesion detectability (p > 0.05). The SubtlePET® algorithm significantly decreased lesion SUV (p < 0.005) and increased liver background (p < 0.005) and had no substantial effect on the diagnostic performance of each reader.

CONCLUSION

We show that the SubtlePET® can be used for ⁶⁸ Ga-PSMA scans using half the signal with similar image quality to Q.Clear series and superior quality to VPFX series. However, it significantly modifies quantitative measurements and should not be used for comparative examinations if standard algorithm is applied during follow-up.

Deep learning-based dynamic PET parametric Ki image generation from lung static PET

OBJECTIVES

PET/CT is a first-line tool for the diagnosis of lung cancer. The accuracy of quantification may suffer from various factors throughout the acquisition process. The dynamic PET parametric K_i provides better quantification and improve specificity for cancer detection. However, parametric imaging is difficult to implement clinically due to the long acquisition time (~ 1 h). We propose a dynamic parametric imaging method based on conventional static PET using deep learning.

METHODS

Based on the imaging data of 203 participants, an improved cycle generative adversarial network incorporated with squeeze-and-excitation attention block was introduced to learn the potential mapping relationship between static PET and K_i parametric images. The image quality of the synthesized images was qualitatively and quantitatively evaluated by using several physical and clinical metrics. Statistical analysis of correlation and consistency was also performed on the synthetic images.

RESULTS

Compared with those of other networks, the images synthesized by our proposed network exhibited superior performance in both qualitative and quantitative evaluation, statistical analysis, and clinical scoring. Our synthesized K_i images had significant correlation (Pearson correlation coefficient, 0.93), consistency, and excellent quantitative evaluation results with the K_i images obtained in standard dynamic PET practice.

CONCLUSIONS

Our proposed deep learning method can be used to synthesize highly correlated and consistent dynamic parametric images obtained from static lung PET.

KEY POINTS

• Compared with conventional static PET, dynamic PET parametric K_i imaging has been shown to provide better quantification and improved specificity for cancer detection. • The purpose of this work was to develop a dynamic parametric imaging method based on static PET images using deep learning. • Our proposed network can synthesize highly correlated and consistent dynamic parametric images, providing an additional quantitative diagnostic reference for clinicians.

Dose evaluation of the one-year-old child in PET imaging by18F-(DOPA, FDG, FLT, FET) and68Ga-EDTA using reference voxel phantoms

Because of more sensitive organs due to high growth rates, evaluating the absorbed dose is essential for children to prevent irreparable damage. Therefore, to this aim, a one-year-old child's whole-body effective dose and organ absorbed dose were evaluated for various PET imaging Radiopharmaceuticals such as:¹⁸F-DOPA,¹⁸F-FDG,¹⁸F-FLT,¹⁸F-FET, and⁶⁸Ga-EDTA. For this aim, one-year-old child reference voxel phantoms and GATE Monte Carlo simulation were used, and the results were compared with the ICRP128 report (for stylized phantom). The highest absorbed dose was related to bladder wall (for¹⁸F-DOPA,¹⁸F-FET, and⁶⁸Ga-EDTA), heart wall (for¹⁸F-FDG), and liver (for¹⁸F-FLT) between 30 organs that have been studied. Comparing the results with the ICRP128 report values for a one-year-old child show a significant difference in some organs. Comparison of the effective dose with the ICRP128 report shows a relative difference of 22%, 12.5%, 11.8%, 10.8% and 8.6% for¹⁸F-DOPA,⁶⁸Ga-EDTA,¹⁸F-FDG,¹⁸F-FET,¹⁸F-FLT, respectively. In conclusion, using new one-year-old voxel phantoms could provide a better estimate of organs absorbed dose and whole-body effective dose due to its exact structure.

Fully automated accurate patient positioning in computed tomography using anterior-posterior localizer images and a deep neural network: a dual-center study

OBJECTIVES

This study aimed to improve patient positioning accuracy by relying on a CT localizer and a deep neural network to optimize image quality and radiation dose.

METHODS

We included 5754 chest CT axial and anterior-posterior (AP) images from two different centers, C1 and C2. After pre-processing, images were split into training (80%) and test (20%) datasets. A deep neural network was trained to generate 3D axial images from the AP localizer. The geometric centerlines of patient bodies were indicated by creating a bounding box on the predicted images. The distance between the body centerline, estimated by the deep learning model and ground truth (BCAP), was compared with patient mis-centering during manual positioning (BCMP). We evaluated the performance of our model in terms of distance between the lung centerline estimated by the deep learning model and the ground truth (LCAP).

RESULTS

The error in terms of BCAP was - 0.75 ± 7.73 mm and 2.06 ± 10.61 mm for C1 and C2, respectively. This error was significantly lower than BCMP, which achieved an error of 9.35 ± 14.94 and 13.98 ± 14.5 mm for C1 and C2, respectively. The absolute BCAP was 5.7 ± 5.26 and 8.26 ± 6.96 mm for C1 and C2, respectively. The LCAP metric was 1.56 ± 10.8 and -0.27 ± 16.29 mm for C1 and C2, respectively. The error in terms of BCAP and LCAP was higher for larger patients (p value < 0.01).

CONCLUSION

The accuracy of the proposed method was comparable to available alternative methods, carrying the advantage of being free from errors related to objects blocking the camera visibility.

KEY POINTS

• Patient mis-centering in the anterior-posterior direction (AP) is a common problem in clinical practice which can degrade image quality and increase patient radiation dose. • We proposed a deep neural network for automatic patient positioning using only the CT image localizer, achieving a performance comparable to alternative techniques, such as the external 3D visual camera. • The advantage of the proposed method is that it is free from errors related to objects blocking the camera visibility and that it could be implemented on imaging consoles as a patient positioning support tool.

Ultra-low-dose CT reconstructed with the artificial intelligence iterative reconstruction algorithm (AIIR) in 18F-FDG total-body PET/CT examination: a preliminary study

PURPOSE

To investigate the feasibility of ultra-low-dose CT (ULDCT) reconstructed with the artificial intelligence iterative reconstruction (AIIR) algorithm in total-body PET/CT imaging.

METHODS

The study included both the phantom and clinical parts. An anthropomorphic phantom underwent CT imaging with ULDCT (10mAs) and standard-dose CT (SDCT) (120mAs), respectively. ULDCT was reconstructed with AIIR and hybrid iterative reconstruction (HIR) (expressed as ULDCT-AIIR_phantom and ULDCT-HIR_phantom), respectively, and SDCT was reconstructed with HIR (SDCT-HIR_phantom) as control. In the clinical part, 52 patients with malignant tumors underwent the total-body PET/CT scan. ULDCT with AIIR (ULDCT-AIIR) and HIR (ULDCT-HIR), respectively, was reconstructed for PET attenuation correction, followed by the SDCT reconstructed with HIR (SDCT-HIR) for anatomical location. PET/CT images' quality was qualitatively assessed by two readers. The CT_mean, as well as the CT standard deviation (CT_sd), SUV_max, SUV_mean, and the SUV standard deviation (SUV_sd), was recorded. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated and compared.

RESULTS

The image quality of ULDCT-HIR_phantom was inferior to the SDCT-HIR_phantom, but no significant difference was found between the ULDCT-AIIR_phantom and SDCT-HIR_phantom. The subjective score of ULDCT-AIIR in the neck, chest and lower limb was equivalent to that of SDCT-HIR. Besides the brain and lower limb, the change rates of CT_mean in thyroid, neck muscle, lung, mediastinum, back muscle, liver, lumbar muscle, first lumbar spine and sigmoid colon were -2.15, -1.52, 0.66, 2.97, 0.23, 8.91, 0.06, -4.29 and 8.78%, respectively, while all CT_sd of ULDCT-AIIR was lower than that of SDCT-HIR. Except for the brain, the CNR of ULDCT-AIIR was the same as the SDCT-HIR, but the SNR was higher. The change rates of SUV_max, SUV_mean and SUV_sd were within [Formula: see text] 3% in all ROIs. For the lesions, the SUV_max, SUV_sd and TBR showed no significant difference between PET-AIIR and PET-HIR.

CONCLUSION

The SDCT-HIR could not be replaced by the ULDCT-AIIR at date, but the AIIR algorithm decreased the image noise and increased the SNR, which can be implemented under special circumstances in PET/CT examination.

Deep progressive learning achieves whole-body low-dose 18F-FDG PET imaging

Objectives

To validate a total-body PET-guided deep progressive learning reconstruction method (DPR) for low-dose 18F-FDG PET imaging.

Methods

List-mode data from the retrospective study (n = 26) were rebinned into short-duration scans and reconstructed with DPR. The standard uptake value (SUV) and tumor-to-liver ratio (TLR) in lesions and coefficient of variation (COV) in the liver in the DPR images were compared to the reference (OSEM images with full-duration data). In the prospective study, another 41 patients were injected with 1/3 of the activity based on the retrospective results. The DPR images (DPR_1/3(p)) were generated and compared with the reference (OSEM images with extended acquisition time). The SUV and COV were evaluated in three selected organs: liver, blood pool and muscle. Quantitative analyses were performed with lesion SUV and TLR, furthermore on small lesions (≤ 10 mm in diameter). Additionally, a 5-point Likert scale visual analysis was performed on the following perspectives: contrast, noise and diagnostic confidence.

Results

In the retrospective study, the DPR with one-third duration can maintain the image quality as the reference. In the prospective study, good agreement among the SUVs was observed in all selected organs. The quantitative results showed that there was no significant difference in COV between the DPR_1/3(p) group and the reference, while the visual analysis showed no significant differences in image contrast, noise and diagnostic confidence. The lesion SUVs and TLRs in the DPR_1/3(p) group were significantly enhanced compared with the reference, even for small lesions.

Conclusions

The proposed DPR method can reduce the administered activity of 18F-FDG by up to 2/3 in a real-world deployment while maintaining image quality.

Measurement Accuracy and Repeatability of RECIST-Defined Pulmonary Lesions and Lymph Nodes in Ultra-Low-Dose CT Based on Deep Learning Image Reconstruction

BACKGROUND

Deep learning image reconstruction (DLIR) improves image quality. We aimed to compare the measured diameter of pulmonary lesions and lymph nodes between DLIR-based ultra-low-dose CT (ULDCT) and contrast-enhanced CT.

METHODS

The consecutive adult patients with noncontrast chest ULDCT (0.07-0.14 mSv) and contrast-enhanced CT (2.38 mSv) were prospectively enrolled. Patients with poor image quality and body mass index ≥ 30 kg/m2 were excluded. The diameter of pulmonary target lesions and lymph nodes defined by Response Evaluation Criteria in Solid Tumors (RECIST) was measured. The measurement variability between ULDCT and enhanced CT was evaluated by Bland-Altman analysis.

RESULTS

The 141 enrolled patients (62 ± 12 years) had 89 RECIST-defined measurable pulmonary target lesions (including 30 malignant lesions, mainly adenocarcinomas) and 45 measurable mediastinal lymph nodes (12 malignant). The measurement variation of pulmonary lesions between high-strength DLIR (DLIR-H) images of ULDCT and contrast-enhanced CT was 2.2% (95% CI: 1.7% to 2.6%) and the variation of lymph nodes was 1.4% (1.0% to 1.9%).

CONCLUSIONS

The measured diameters of pulmonary lesions and lymph nodes in DLIR-H images of ULDCT are highly close to those of contrast-enhanced CT. DLIR-based ULDCT may facilitate evaluating target lesions with greatly reduced radiation exposure in tumor evaluation and lung cancer screening.

Deep-TOF-PET: Deep learning-guided generation of time-of-flight from non-TOF brain PET images in the image and projection domains

We aim to synthesize brain time‐of‐flight (TOF) PET images/sinograms from their corresponding non‐TOF information in the image space (IS) and sinogram space (SS) to increase the signal‐to‐noise ratio (SNR) and contrast of abnormalities, and decrease the bias in tracer uptake quantification. One hundred forty clinical brain ¹⁸F‐FDG PET/CT scans were collected to generate TOF and non‐TOF sinograms. The TOF sinograms were split into seven time bins (0, ±1, ±2, ±3). The predicted TOF sinogram was reconstructed and the performance of both models (IS and SS) compared with reference TOF and non‐TOF. Wide‐ranging quantitative and statistical analysis metrics, including structural similarity index metric (SSIM), root mean square error (RMSE), as well as 28 radiomic features for 83 brain regions were extracted to evaluate the performance of the CycleGAN model. SSIM and RMSE of 0.99 ± 0.03, 0.98 ± 0.02 and 0.12 ± 0.09, 0.16 ± 0.04 were achieved for the generated TOF‐PET images in IS and SS, respectively. They were 0.97 ± 0.03 and 0.22 ± 0.12, respectively, for non‐TOF‐PET images. The Bland & Altman analysis revealed that the lowest tracer uptake value bias (−0.02%) and minimum variance (95% CI: −0.17%, +0.21%) were achieved for TOF‐PET images generated in IS. For malignant lesions, the contrast in the test dataset was enhanced from 3.22 ± 2.51 for non‐TOF to 3.34 ± 0.41 and 3.65 ± 3.10 for TOF PET in SS and IS, respectively. The implemented CycleGAN is capable of generating TOF from non‐TOF PET images to achieve better image quality.

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

PURPOSE

Recently, deep learning-based methods have been established to denoise the low-count positron emission tomography (PET) images and predict their standard-count image counterparts, which could achieve reduction of injected dosage and scan time, and improve image quality for equivalent lesion detectability and clinical diagnosis. In clinical settings, the majority scans are still acquired using standard injection dose with standard scan time. In this work, we applied a 3D U-Net network to reduce the noise of standard-count PET images to obtain the virtual-high-count (VHC) PET images for identifying the potential benefits of the obtained VHC PET images.

METHODS

The training datasets, including down-sampled standard-count PET images as the network input and high-count images as the desired network output, were derived from 27 whole-body PET datasets, which were acquired using 90-min dynamic scan. The down-sampled standard-count PET images were rebinned with matched noise level of 195 clinical static PET datasets, by matching the normalized standard derivation (NSTD) inside 3D liver region of interests (ROIs). Cross-validation was performed on 27 PET datasets. Normalized mean square error (NMSE), peak signal to noise ratio (PSNR), structural similarity index (SSIM), and standard uptake value (SUV) bias of lesions were used for evaluation on standard-count and VHC PET images, with real-high-count PET image of 90 min as the gold standard. In addition, the network trained with 27 dynamic PET datasets was applied to 195 clinical static datasets to obtain VHC PET images. The NSTD and mean/max SUV of hypermetabolic lesions in standard-count and VHC PET images were evaluated. Three experienced nuclear medicine physicians evaluated the overall image quality of randomly selected 50 out of 195 patients' standard-count and VHC images and conducted 5-score ranking. A Wilcoxon signed-rank test was used to compare differences in the grading of standard-count and VHC images.

RESULTS

The cross-validation results showed that VHC PET images had improved quantitative metrics scores than the standard-count PET images. The mean/max SUVs of 35 lesions in the standard-count and true-high-count PET images did not show significantly statistical difference. Similarly, the mean/max SUVs of VHC and true-high-count PET images did not show significantly statistical difference. For the 195 clinical data, the VHC PET images had a significantly lower NSTD than the standard-count images. The mean/max SUVs of 215 hypermetabolic lesions in the VHC and standard-count images showed no statistically significant difference. In the image quality evaluation by three experienced nuclear medicine physicians, standard-count images and VHC images received scores with mean and standard deviation of 3.34±0.80 and 4.26 ± 0.72 from Physician 1, 3.02 ± 0.87 and 3.96 ± 0.73 from Physician 2, and 3.74 ± 1.10 and 4.58 ± 0.57 from Physician 3, respectively. The VHC images were consistently ranked higher than the standard-count images. The Wilcoxon signed-rank test also indicated that the image quality evaluation between standard-count and VHC images had significant difference.

CONCLUSIONS

A DL method was proposed to convert the standard-count images to the VHC images. The VHC images had reduced noise level. No significant difference in mean/max SUV to the standard-count images was observed. VHC images improved image quality for better lesion detectability and clinical diagnosis.

Phantom-based acquisition time and image reconstruction parameter optimisation for oncologic FDG PET/CT examinations using a digital system

Background

New-generation silicon-photomultiplier (SiPM)-based PET/CT systems exhibit an improved lesion detectability and image quality due to a higher detector sensitivity. Consequently, the acquisition time can be reduced while maintaining diagnostic quality. The aim of this study was to determine the lowest ¹⁸F-FDG PET acquisition time without loss of diagnostic information and to optimise image reconstruction parameters (image reconstruction algorithm, number of iterations, voxel size, Gaussian filter) by phantom imaging. Moreover, patient data are evaluated to confirm the phantom results.

Methods

Three phantoms were used: a soft-tissue tumour phantom, a bone-lung tumour phantom, and a resolution phantom. Phantom conditions (lesion sizes from 6.5 mm to 28.8 mm in diameter, lesion activity concentration of 15 kBq/mL, and signal-to-background ratio of 5:1) were derived from patient data. PET data were acquired on an SiPM-based Biograph Vision PET/CT system for 10 min in list-mode format and resampled into time frames from 30 to 300 s in 30-s increments to simulate different acquisition times. Different image reconstructions with varying iterations, voxel sizes, and Gaussian filters were probed. Contrast-to-noise-ratio (CNR), maximum, and peak signal were evaluated using the 10-min acquisition time image as reference. A threshold CNR value ≥ 5 and a maximum (peak) deviation of ± 20% were considered acceptable. 20 patient data sets were evaluated regarding lesion quantification as well as agreement and correlation between reduced and full acquisition time standard uptake values (assessed by Pearson correlation coefficient, intraclass correlation coefficient, Bland–Altman analyses, and Krippendorff’s alpha).

Results

An acquisition time of 60 s per bed position yielded acceptable detectability and quantification results for clinically relevant phantom lesions ≥ 9.7 mm in diameter using OSEM-TOF or OSEM-TOF+PSF image reconstruction, a 4-mm Gaussian filter, and a 1.65 × 1.65 x 2.00-mm³ or 3.30 × 3.30 x 3.00-mm³ voxel size. Correlation and agreement of patient lesion quantification between full and reduced acquisition times were excellent.

Conclusion

A threefold reduction in acquisition time is possible. Patients might benefit from more comfortable examinations or reduced radiation exposure, if instead of the acquisition time the applied activity is reduced.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-022-09993-4.

Artificial intelligence guided enhancement of digital PET: scans as fast as CT?

Purpose

Both digital positron emission tomography (PET) detector technologies and artificial intelligence based image post-reconstruction methods allow to reduce the PET acquisition time while maintaining diagnostic quality. The aim of this study was to acquire ultra-low-count fluorodeoxyglucose (FDG) ExtremePET images on a digital PET/computed tomography (CT) scanner at an acquisition time comparable to a CT scan and to generate synthetic full-dose PET images using an artificial neural network.

Methods

This is a prospective, single-arm, single-center phase I/II imaging study. A total of 587 patients were included. For each patient, a standard and an ultra-low-count FDG PET/CT scan (whole-body acquisition time about 30 s) were acquired. A modified pix2pixHD deep-learning network was trained employing 387 data sets as training and 200 as test cohort. Three models (PET-only and PET/CT with or without group convolution) were compared. Detectability and quantification were evaluated.

Results

The PET/CT input model with group convolution performed best regarding lesion signal recovery and was selected for detailed evaluation. Synthetic PET images were of high visual image quality; mean absolute lesion SUV_max (maximum standardized uptake value) difference was 1.5. Patient-based sensitivity and specificity for lesion detection were 79% and 100%, respectively. Not-detected lesions were of lower tracer uptake and lesion volume. In a matched-pair comparison, patient-based (lesion-based) detection rate was 89% (78%) for PERCIST (PET response criteria in solid tumors)-measurable and 36% (22%) for non PERCIST-measurable lesions.

Conclusion

Lesion detectability and lesion quantification were promising in the context of extremely fast acquisition times. Possible application scenarios might include re-staging of late-stage cancer patients, in whom assessment of total tumor burden can be of higher relevance than detailed evaluation of small and low-uptake lesions.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-022-05901-x.

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.

Comparison of the performances of machine learning and deep learning in improving the quality of low dose lung cancer PET images

PURPOSE

To compare the performances of machine learning (ML) and deep learning (DL) in improving the quality of low dose (LD) lung cancer PET images and the minimum counts required.

MATERIALS AND METHODS

33 standard dose (SD) PET images, were used to simulate LD PET images at seven-count levels of 0.25, 0.5, 1, 2, 5, 7.5 and 10 million (M) counts. Image quality transfer (IQT), a ML algorithm that uses decision tree and patch-sampling was compared to two DL networks-HighResNet (HRN) and deep-boosted regression (DBR). Supervised training was performed by training the ML and DL algorithms with matched-pair SD and LD images. Image quality evaluation and clinical lesion detection tasks were performed by three readers. Bias in 53 radiomic features, including mean SUV, was evaluated for all lesions.

RESULTS

ML- and DL-estimated images showed higher signal and smaller error than LD images with optimal image quality recovery achieved using LD down to 5 M counts. True positive rate and false discovery rate were fairly stable beyond 5 M counts for the detection of small and large true lesions. Readers rated average or higher ratings to images estimated from LD images of count levels above 5 M only, with higher confidence in detecting true lesions.

CONCLUSION

LD images with a minimum of 5 M counts (8.72 MBq for 10 min scan or 25 MBq for 3 min scan) are required for optimal clinical use of ML and DL, with slightly better but more varied performance shown by DL.

Evaluation of a High-Sensitivity Organ-Targeted PET Camera

The aim of this study is to evaluate the performance of the Radialis organ-targeted positron emission tomography (PET) Camera with standardized tests and through assessment of clinical-imaging results. Sensitivity, count-rate performance, and spatial resolution were evaluated according to the National Electrical Manufacturers Association (NEMA) NU-4 standards, with necessary modifications to accommodate the planar detector design. The detectability of small objects was shown with micro hotspot phantom images. The clinical performance of the camera was also demonstrated through breast cancer images acquired with varying injected doses of 2-[fluorine-18]-fluoro-2-deoxy-D-glucose (¹⁸F-FDG) and qualitatively compared with sample digital full-field mammography, magnetic resonance imaging (MRI), and whole-body (WB) PET images. Micro hotspot phantom sources were visualized down to 1.35 mm-diameter rods. Spatial resolution was calculated to be 2.3 ± 0.1 mm for the in-plane resolution and 6.8 ± 0.1 mm for the cross-plane resolution using maximum likelihood expectation maximization (MLEM) reconstruction. The system peak noise equivalent count rate was 17.8 kcps at a ¹⁸F-FDG concentration of 10.5 kBq/mL. System scatter fraction was 24%. The overall efficiency at the peak noise equivalent count rate was 5400 cps/MBq. The maximum axial sensitivity achieved was 3.5%, with an average system sensitivity of 2.4%. Selected results from clinical trials demonstrate capability of imaging lesions at the chest wall and identifying false-negative X-ray findings and false-positive MRI findings, even at up to a 10-fold dose reduction in comparison with standard ¹⁸F-FDG doses (i.e., at 37 MBq or 1 mCi). The evaluation of the organ-targeted Radialis PET Camera indicates that it is a promising technology for high-image-quality, low-dose PET imaging. High-efficiency radiotracer detection also opens an opportunity to reduce administered doses of radiopharmaceuticals and, therefore, patient exposure to radiation.

Robust-Deep: A Method for Increasing Brain Imaging Datasets to Improve Deep Learning Models' Performance and Robustness

A small dataset commonly affects generalization, robustness, and overall performance of deep neural networks (DNNs) in medical imaging research. Since gathering large clinical databases is always difficult, we proposed an analytical method for producing a large realistic/diverse dataset. Clinical brain PET/CT/MR images including full-dose (FD), low-dose (LD) corresponding to only 5 % of events acquired in the FD scan, non-attenuated correction (NAC) and CT-based measured attenuation correction (MAC) PET images, CT images and T1 and T2 MR sequences of 35 patients were included. All images were registered to the Montreal Neurological Institute (MNI) template. Laplacian blending was used to make a natural presentation using information in the frequency domain of images from two separate patients, as well as the blending mask. This classical technique from the computer vision and image processing communities is still widely used and unlike modern DNNs, does not require the availability of training data. A modified ResNet DNN was implemented to evaluate four image-to-image translation tasks, including LD to FD, LD+MR to FD, NAC to MAC, and MRI to CT, with and without using the synthesized images. Quantitative analysis using established metrics, including the peak signal-to-noise ratio (PSNR), structural similarity index metric (SSIM), and joint histogram analysis was performed for quantitative evaluation. The quantitative comparison between the registered small dataset containing 35 patients and the large dataset containing 350 synthesized plus 35 real dataset demonstrated improvement of the RMSE and SSIM by 29% and 8% for LD to FD, 40% and 7% for LD+MRI to FD, 16% and 8% for NAC to MAC, and 24% and 11% for MRI to CT mapping task, respectively. The qualitative/quantitative analysis demonstrated that the proposed model improved the performance of all four DNN models through producing images of higher quality and lower quantitative bias and variance compared to reference images.

Artificial intelligence-based PET denoising could allow a two-fold reduction in [18F]FDG PET acquisition time in digital PET/CT

Purpose

We investigated whether artificial intelligence (AI)-based denoising halves PET acquisition time in digital PET/CT.

Methods

One hundred ninety-five patients referred for [¹⁸F]FDG PET/CT were prospectively included. Body PET acquisitions were performed in list mode. Original “PET90” (90 s/bed position) was compared to reconstructed ½-duration PET (45 s/bed position) with and without AI-denoising, “PET45AI and PET45”. Denoising was performed by SubtlePET™ using deep convolutional neural networks. Visual global image quality (IQ) 3-point scores and lesion detectability were evaluated. Lesion maximal and peak standardized uptake values using lean body mass (SUL_max and SUL_peak), metabolic volumes (MV), and liver SUL_mean were measured, including both standard and EARL₁ (European Association of Nuclear Medicine Research Ltd) compliant SUL. Lesion-to-liver SUL ratios (LLR) and liver coefficients of variation (CV_liv) were calculated.

Results

PET45 showed mediocre IQ (scored poor in 8% and moderate in 68%) and lesion concordance rate with PET90 (88.7%). In PET45AI, IQ scores were similar to PET90 (P = 0.80), good in 92% and moderate in 8% for both. The lesion concordance rate between PET90 and PET45AI was 836/856 (97.7%), with 7 lesions (0.8%) only detected in PET90 and 13 (1.5%) exclusively in PET45AI. Lesion EARL₁ SUL_peak was not significantly different between both PET (P = 0.09). Lesion standard SUL_peak, standard and EARL1 SUL_max, LLR and CV_liv were lower in PET45AI than in PET90 (P < 0.0001), while lesion MV and liver SUL_mean were higher (P < 0.0001). Good to excellent intraclass correlation coefficients (ICC) between PET90 and PET45AI were observed for lesion SUL and MV (ICC ≥ 0.97) and for liver SUL_mean (ICC ≥ 0.87).

Conclusion

AI allows [¹⁸F]FDG PET duration in digital PET/CT to be halved, while restoring degraded ½-duration PET image quality. Future multicentric studies, including other PET radiopharmaceuticals, are warranted.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-022-05800-1.

Applications of Generative Adversarial Networks (GANs) in Positron Emission Tomography (PET) imaging: A review

PURPOSE

This paper reviews recent applications of Generative Adversarial Networks (GANs) in Positron Emission Tomography (PET) imaging. Recent advances in Deep Learning (DL) and GANs catalysed the research of their applications in medical imaging modalities. As a result, several unique GAN topologies have emerged and been assessed in an experimental environment over the last two years.

METHODS

The present work extensively describes GAN architectures and their applications in PET imaging. The identification of relevant publications was performed via approved publication indexing websites and repositories. Web of Science, Scopus, and Google Scholar were the major sources of information.

RESULTS

The research identified a hundred articles that address PET imaging applications such as attenuation correction, de-noising, scatter correction, removal of artefacts, image fusion, high-dose image estimation, super-resolution, segmentation, and cross-modality synthesis. These applications are presented and accompanied by the corresponding research works.

CONCLUSION

GANs are rapidly employed in PET imaging tasks. However, specific limitations must be eliminated to reach their full potential and gain the medical community's trust in everyday clinical practice.

Decentralized Distributed Multi-institutional PET Image Segmentation Using a Federated Deep Learning Framework

PURPOSE

The generalizability and trustworthiness of deep learning (DL)-based algorithms depend on the size and heterogeneity of training datasets. However, because of patient privacy concerns and ethical and legal issues, sharing medical images between different centers is restricted. Our objective is to build a federated DL-based framework for PET image segmentation utilizing a multicentric dataset and to compare its performance with the centralized DL approach.

METHODS

PET images from 405 head and neck cancer patients from 9 different centers formed the basis of this study. All tumors were segmented manually. PET images converted to SUV maps were resampled to isotropic voxels (3 × 3 × 3 mm3) and then normalized. PET image subvolumes (12 × 12 × 12 cm3) consisting of whole tumors and background were analyzed. Data from each center were divided into train/validation (80% of patients) and test sets (20% of patients). The modified R2U-Net was used as core DL model. A parallel federated DL model was developed and compared with the centralized approach where the data sets are pooled to one server. Segmentation metrics, including Dice similarity and Jaccard coefficients, percent relative errors (RE%) of SUVpeak, SUVmean, SUVmedian, SUVmax, metabolic tumor volume, and total lesion glycolysis were computed and compared with manual delineations.

RESULTS

The performance of the centralized versus federated DL methods was nearly identical for segmentation metrics: Dice (0.84 ± 0.06 vs 0.84 ± 0.05) and Jaccard (0.73 ± 0.08 vs 0.73 ± 0.07). For quantitative PET parameters, we obtained comparable RE% for SUVmean (6.43% ± 4.72% vs 6.61% ± 5.42%), metabolic tumor volume (12.2% ± 16.2% vs 12.1% ± 15.89%), and total lesion glycolysis (6.93% ± 9.6% vs 7.07% ± 9.85%) and negligible RE% for SUVmax and SUVpeak. No significant differences in performance (P > 0.05) between the 2 frameworks (centralized vs federated) were observed.

CONCLUSION

The developed federated DL model achieved comparable quantitative performance with respect to the centralized DL model. Federated DL models could provide robust and generalizable segmentation, while addressing patient privacy and legal and ethical issues in clinical data sharing.

A review on AI in PET imaging

Artificial intelligence (AI) has been applied to various medical imaging tasks, such as computer-aided diagnosis. Specifically, deep learning techniques such as convolutional neural network (CNN) and generative adversarial network (GAN) have been extensively used for medical image generation. Image generation with deep learning has been investigated in studies using positron emission tomography (PET). This article reviews studies that applied deep learning techniques for image generation on PET. We categorized the studies for PET image generation with deep learning into three themes as follows: (1) recovering full PET data from noisy data by denoising with deep learning, (2) PET image reconstruction and attenuation correction with deep learning and (3) PET image translation and synthesis with deep learning. We introduce recent studies based on these three categories. Finally, we mention the limitations of applying deep learning techniques to PET image generation and future prospects for PET image generation.

Clinical Use of PET/MR in Oncology: An Update

The combination of PET and MRI is one of the recent advances of hybrid imaging. Yet to date, the adoption rate of PET/MRI systems has been rather slow. This seems to be partially caused by the high costs of PET/MRI systems and the need to verify an incremental benefit over PET/CT or sequential PET/CT and MRI. In analogy to PET/CT, the MRI part of PET/MRI was primarily used for anatomical imaging. Though this can be advantageous, for example in diseases where the superior soft tissue contrast of MRI is highly appreciated, the sole use of MRI for anatomical orientation lessens the potential of PET/MRI. Consequently, more recent studies focused on its multiparametric potential and employed diffusion weighted sequences and other functional imaging sequences in PET/MRI. This integration puts the focus on a more wholesome approach to PET/MR imaging, in terms of releasing its full potential for local primary staging based on multiparametric imaging and an included one-stop shop approach for whole-body staging. This approach as well as the implementation of computational analysis, in terms of radiomics analysis, has been shown valuable in several oncological diseases, as will be discussed in this review article.

Advances in PET-CT technology: An update

This article reviews the current evolution and future directions in PET-CT technology focusing on three areas: time of flight, image reconstruction, and data-driven gating. Image reconstruction is considered with advances in point spread function modelling, Bayesian penalised likelihood reconstruction, and artificial intelligence approaches. Data-driven gating is examined with reference to respiratory motion, cardiac motion, and head motion. For each of these technological advancements, theory will be briefly discussed, benefits of their use in routine practice will be detailed and potential future developments will be discussed. Representative clinical cases will be presented, demonstrating the huge opportunities given to the PET community by hardware and software advances in PET technology when it comes to lesion detection, disease characterization, accurate quantitation and quicker scans. Through this review, hospitals are encouraged to embrace, evaluate and appropriately implement the wide range of new PET technologies that are available now or in the near future, for the improvement of patient care.

Leveraging deep neural networks to improve numerical and perceptual image quality in low-dose preclinical PET imaging

The amount of radiotracer injected into laboratory animals is still the most daunting challenge facing translational PET studies. Since low-dose imaging is characterized by a higher level of noise, the quality of the reconstructed images leaves much to be desired. Being the most ubiquitous techniques in denoising applications, edge-aware denoising filters, and reconstruction-based techniques have drawn significant attention in low-count applications. However, for the last few years, much of the credit has gone to deep-learning (DL) methods, which provide more robust solutions to handle various conditions. Albeit being extensively explored in clinical studies, to the best of our knowledge, there is a lack of studies exploring the feasibility of DL-based image denoising in low-count small animal PET imaging. Therefore, herein, we investigated different DL frameworks to map low-dose small animal PET images to their full-dose equivalent with quality and visual similarity on a par with those of standard acquisition. The performance of the DL model was also compared to other well-established filters, including Gaussian smoothing, nonlocal means, and anisotropic diffusion. Visual inspection and quantitative assessment based on quality metrics proved the superior performance of the DL methods in low-count small animal PET studies, paving the way for a more detailed exploration of DL-assisted algorithms in this domain.

DeepTOFSino: A deep learning model for synthesizing full-dose time-of-flight bin sinograms from their corresponding low-dose sinograms

PURPOSE

Reducing the injected activity and/or the scanning time is a desirable goal to minimize radiation exposure and maximize patients' comfort. To achieve this goal, we developed a deep neural network (DNN) model for synthesizing full-dose (FD) time-of-flight (TOF) bin sinograms from their corresponding fast/low-dose (LD) TOF bin sinograms.

METHODS

Clinical brain PET/CT raw data of 140 normal and abnormal patients were employed to create LD and FD TOF bin sinograms. The LD TOF sinograms were created through 5% undersampling of FD list-mode PET data. The TOF sinograms were split into seven time bins (0, ±1, ±2, ±3). Residual network (ResNet) algorithms were trained separately to generate FD bins from LD bins. An extra ResNet model was trained to synthesize FD images from LD images to compare the performance of DNN in sinogram space (SS) vs implementation in image space (IS). Comprehensive quantitative and statistical analysis was performed to assess the performance of the proposed model using established quantitative metrics, including the peak signal-to-noise ratio (PSNR), structural similarity index metric (SSIM) region-wise standardized uptake value (SUV) bias and statistical analysis for 83 brain regions.

RESULTS

SSIM and PSNR values of 0.97 ± 0.01, 0.98 ± 0.01 and 33.70 ± 0.32, 39.36 ± 0.21 were obtained for IS and SS, respectively, compared to 0.86 ± 0.02and 31.12 ± 0.22 for reference LD images. The absolute average SUV bias was 0.96 ± 0.95% and 1.40 ± 0.72% for SS and IS implementations, respectively. The joint histogram analysis revealed the lowest mean square error (MSE) and highest correlation (R² = 0.99, MSE = 0.019) was achieved by SS compared to IS (R² = 0.97, MSE= 0.028). The Bland & Altman analysis showed that the lowest SUV bias (-0.4%) and minimum variance (95% CI: -2.6%, +1.9%) were achieved by SS images. The voxel-wise t-test analysis revealed the presence of voxels with statistically significantly lower values in LD, IS, and SS images compared to FD images respectively.

CONCLUSION

The results demonstrated that images reconstructed from the predicted TOF FD sinograms using the SS approach led to higher image quality and lower bias compared to images predicted from LD images.

Artificial Intelligence-Based Image Enhancement in PET Imaging: Noise Reduction and Resolution Enhancement

High noise and low spatial resolution are two key confounding factors that limit the qualitative and quantitative accuracy of PET images. Artificial intelligence models for image denoising and deblurring are becoming increasingly popular for the postreconstruction enhancement of PET images. We present a detailed review of recent efforts for artificial intelligence-based PET image enhancement with a focus on network architectures, data types, loss functions, and evaluation metrics. We also highlight emerging areas in this field that are quickly gaining popularity, identify barriers to large-scale adoption of artificial intelligence models for PET image enhancement, and discuss future directions.

The Evolution of Image Reconstruction in PET: From Filtered Back-Projection to Artificial Intelligence

PET can provide functional images revealing physiologic processes in vivo. Although PET has many applications, there are still some limitations that compromise its precision: the absorption of photons in the body causes signal attenuation; the dead-time limit of system components leads to the loss of the count rate; the scattered and random events received by the detector introduce additional noise; the characteristics of the detector limit the spatial resolution; and the low signal-to-noise ratio caused by the scan-time limit (eg, dynamic scans) and dose concern. The early PET reconstruction methods are analytical approaches based on an idealized mathematical model.

Artificial intelligence-driven assessment of radiological images for COVID-19

Artificial Intelligence (AI) methods have significant potential for diagnosis and prognosis of COVID-19 infections. Rapid identification of COVID-19 and its severity in individual patients is expected to enable better control of the disease individually and at-large. There has been remarkable interest by the scientific community in using imaging biomarkers to improve detection and management of COVID-19. Exploratory tools such as AI-based models may help explain the complex biological mechanisms and provide better understanding of the underlying pathophysiological processes. The present review focuses on AI-based COVID-19 studies as applies to chest x-ray (CXR) and computed tomography (CT) imaging modalities, and the associated challenges. Explicit radiomics, deep learning methods, and hybrid methods that combine both deep learning and explicit radiomics have the potential to enhance the ability and usefulness of radiological images to assist clinicians in the current COVID-19 pandemic. The aims of this review are: first, to outline COVID-19 AI-analysis workflows, including acquisition of data, feature selection, segmentation methods, feature extraction, and multi-variate model development and validation as appropriate for AI-based COVID-19 studies. Secondly, existing limitations of AI-based COVID-19 analyses are discussed, highlighting potential improvements that can be made. Finally, the impact of AI and radiomics methods and the associated clinical outcomes are summarized. In this review, pipelines that include the key steps for AI-based COVID-19 signatures identification are elaborated. Sample size, non-standard imaging protocols, segmentation, availability of public COVID-19 databases, combination of imaging and clinical information and full clinical validation remain major limitations and challenges. We conclude that AI-based assessment of CXR and CT images has significant potential as a viable pathway for the diagnosis, follow-up and prognosis of COVID-19.

A dedicated paediatric [18F]FDG PET/CT dosage regimen

BACKGROUND

The role of 2-[¹⁸F]fluoro-2-deoxy-D-glucose ([¹⁸F]FDG) positron emission tomography/computed tomography (PET/CT) in children is still expanding. Dedicated paediatric dosage regimens are needed to keep the radiation dose as low as reasonably achievable and reduce the risk of radiation-induced carcinogenesis. The aim of this study is to investigate the relation between patient-dependent parameters and [¹⁸F]FDG PET image quality in order to propose a dedicated paediatric dose regimen.

METHODS

In this retrospective analysis, 102 children and 85 adults were included that underwent a diagnostic [¹⁸F]FDG PET/CT scan. The image quality of the PET scans was measured by the signal-to-noise ratio (SNR) in the liver. The SNR liver was normalized (SNRnorm) for administered activity and acquisition time to apply curve fitting with body weight, body length, body mass index, body weight/body length and body surface area. Curve fitting was performed with two power fits, a nonlinear two-parameter model α p^-d and a linear single-parameter model α p^-0.5. The fit parameters of the preferred model were combined with a user preferred SNR to obtain at least moderate or good image quality for the dosage regimen proposal.

RESULTS

Body weight demonstrated the highest coefficient of determination for the nonlinear (R² = 0.81) and linear (R² = 0.80) models. The nonlinear model was preferred by the Akaike's corrected information criterion. We decided to use a SNR of 6.5, based on the expert opinion of three nuclear medicine physicians. Comparison with the quadratic adult protocol confirmed the need for different dosage regimens for both patient groups. In this study, the amount of administered activity can be considerably reduced in comparison with the current paediatric guidelines.

CONCLUSION

Body weight has the strongest relation with [¹⁸F]FDG PET image quality in children. The proposed nonlinear dosage regimen based on body mass will provide a constant and clinical sufficient image quality with a significant reduction of the effective dose compared to the current guidelines. A dedicated paediatric dosage regimen is necessary, as a universal dosing regimen for paediatric and adult is not feasible.

Fast dynamic brain PET imaging using stochastic variational prediction for recurrent frame generation

Purpose

We assess the performance of a recurrent frame generation algorithm for prediction of late frames from initial frames in dynamic brain PET imaging.

Methods

Clinical dynamic ¹⁸F‐DOPA brain PET/CT studies of 46 subjects with ten folds cross‐validation were retrospectively employed. A novel stochastic adversarial video prediction model was implemented to predict the last 13 frames (25–90 minutes) from the initial 13 frames (0–25 minutes). The quantitative analysis of the predicted dynamic PET frames was performed for the test and validation dataset using established metrics.

Results

The predicted dynamic images demonstrated that the model is capable of predicting the trend of change in time‐varying tracer biodistribution. The Bland‐Altman plots reported the lowest tracer uptake bias (−0.04) for the putamen region and the smallest variance (95% CI: −0.38, +0.14) for the cerebellum. The region‐wise Patlak graphical analysis in the caudate and putamen regions for eight subjects from the test and validation dataset showed that the average bias for Ki and distribution volume was 4.3%, 5.1% and 4.4%, 4.2%, (P‐value <0.05), respectively.

Conclusion

We have developed a novel deep learning approach for fast dynamic brain PET imaging capable of generating the last 65 minutes time frames from the initial 25 minutes frames, thus enabling significant reduction in scanning time.