Internal dosimetry study of [82Rb]Cl using a long axial field-of-view PET/CT.

PURPOSE: Long axial field-of-view (LAFOV) positron emission tomography (PET) systems allow to image all major organs with one bed position, which is particularly useful for acquiring whole-body dynamic data using short-lived radioisotopes like 82Rb. METHODS: We determined the absorbed dose in target organs of three subjects (29, 40, and 57 years old) using two different methods, i.e., MIRD and voxel dosimetry. The subjects were injected with 407.0 to 419.61 MBq of [82Rb]Cl and were scanned dynamically for 7 min with a LAFOV PET/CT scanner. RESULTS: Using the MIRD formalism and voxel dosimetry, the absorbed dose ranged from 1.84 to 2.78 µGy/MBq (1.57 to 3.92 µGy/MBq for voxel dosimetry) for the heart wall, 2.76 to 5.73 µGy/MBq (3.22 to 5.37 µGy/MBq for voxel dosimetry) for the kidneys, and 0.94 to 1.88 µGy/MBq (0.98 to 1.92 µGy/MBq for voxel dosimetry) for the lungs. The total body effective dose lied between 0.50 and 0.76 µSv/MBq. CONCLUSION: Our study suggests that the radiation dose associated with [82Rb]Cl PET/CT can be assessed by means of dynamic LAFOV PET and that it is lower compared to literature values.

Investigating the influence of long-axial versus short-axial field of view PET/CT on stage migration in lymphoma and non-small cell lung cancer.

OBJECTIVES: The objective of this study was to evaluate the influence of a long-axial field-of-view (LAFOV) on stage migration using a large single-centre retrospective cohort in lymphoma and non-small cell lung cancer (NSCLC). METHODS: A retrospective study is performed for patients undergoing PET/computed tomography (CT) on either a short-axial field-of-view (SAFOV) or LAFOV PET/CT system for the staging of known or suspected NSCLC or for therapeutic response in lymphoma. The primary endpoint was the Deauville therapy response score for patients with lymphoma for the two systems. Secondary endpoints were the American Joint Committee on Cancer stage for NSCLC, the frequency of cN3 and cM1 findings, the probability for a positive nodal staging (cN1-3) for NSCLC and the diagnostic accuracy for nodal staging in NSCLC. RESULTS: One thousand two hundred eighteen records were screened and 597 patients were included for analysis ( N  = 367 for lymphoma and N  = 291 for NSCLC). For lymphoma, no significant differences were found in the proportion of patients with complete metabolic response versus non-complete metabolic response Deauville response scores ( P  = 0.66). For NSCLC no significant differences were observed between the two scanners for the frequency of cN3 and cM1 findings, for positive nodal staging, neither the sensitivity nor the specificity. CONCLUSIONS: In this study use of a LAFOV system was neither associated with upstaging in lymphoma nor NSCLC compared to a digital SAFOV system. Diagnostic accuracy was comparable between the two systems in NSCLC despite shorter acquisition times for LAFOV.

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

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

An encoder-decoder network for direct image reconstruction on sinograms of a long axial field of view PET.

PURPOSE: Deep learning is an emerging reconstruction method for positron emission tomography (PET), which can tackle complex PET corrections in an integrated procedure. This paper optimizes the direct PET reconstruction from sinogram on a long axial field of view (LAFOV) PET. METHODS: This paper proposes a novel deep learning architecture to reduce the biases during direct reconstruction from sinograms to images. This architecture is based on an encoder-decoder network, where the perceptual loss is used with pre-trained convolutional layers. It is trained and tested on data of 80 patients acquired from recent Siemens Biograph Vision Quadra long axial FOV (LAFOV) PET/CT. The patients are randomly split into a training dataset of 60 patients, a validation dataset of 10 patients, and a test dataset of 10 patients. The 3D sinograms are converted into 2D sinogram slices and used as input to the network. In addition, the vendor reconstructed images are considered as ground truths. Finally, the proposed method is compared with DeepPET, a benchmark deep learning method for PET reconstruction. RESULTS: Compared with DeepPET, the proposed network significantly reduces the root-mean-squared error (NRMSE) from 0.63 to 0.6 (p < 0.01) and increases the structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR) from 0.93 to 0.95 (p < 0.01) and from 82.02 to 82.36 (p < 0.01), respectively. The reconstruction time is approximately 10 s per patient, which is shortened by 23 times compared with the conventional method. The errors of mean standardized uptake values (SUVmean) for lesions between ground truth and the predicted result are reduced from 33.5 to 18.7% (p = 0.03). In addition, the error of max SUV is reduced from 32.7 to 21.8% (p = 0.02). CONCLUSION: The results demonstrate the feasibility of using deep learning to reconstruct images with acceptable image quality and short reconstruction time. It is shown that the proposed method can improve the quality of deep learning-based reconstructed images without additional CT images for attenuation and scattering corrections. This study demonstrated the feasibility of deep learning to rapidly reconstruct images without additional CT images for complex corrections from actual clinical measurements on LAFOV PET. Despite improving the current development, AI-based reconstruction does not work appropriately for untrained scenarios due to limited extrapolation capability and cannot completely replace conventional reconstruction currently.

A cross-scanner and cross-tracer deep learning method for the recovery of standard-dose imaging quality from low-dose PET.

PURPOSE: A critical bottleneck for the credibility of artificial intelligence (AI) is replicating the results in the diversity of clinical practice. We aimed to develop an AI that can be independently applied to recover high-quality imaging from low-dose scans on different scanners and tracers. METHODS: Brain [18F]FDG PET imaging of 237 patients scanned with one scanner was used for the development of AI technology. The developed algorithm was then tested on [18F]FDG PET images of 45 patients scanned with three different scanners, [18F]FET PET images of 18 patients scanned with two different scanners, as well as [18F]Florbetapir images of 10 patients. A conditional generative adversarial network (GAN) was customized for cross-scanner and cross-tracer optimization. Three nuclear medicine physicians independently assessed the utility of the results in a clinical setting. RESULTS: The improvement achieved by AI recovery significantly correlated with the baseline image quality indicated by structural similarity index measurement (SSIM) (r = -0.71, p < 0.05) and normalized dose acquisition (r = -0.60, p < 0.05). Our cross-scanner and cross-tracer AI methodology showed utility based on both physical and clinical image assessment (p < 0.05). CONCLUSION: The deep learning development for extensible application on unknown scanners and tracers may improve the trustworthiness and clinical acceptability of AI-based dose reduction.

Development of a deep learning method for CT-free correction for an ultra-long axial field of view PET scanner.

INTRODUCTION: The possibility of low-dose positron emission tomography (PET) imaging using high sensitivity long axial field of view (FOV) PET/computed tomography (CT) scanners makes CT a critical radiation burden in clinical applications. Artificial intelligence has shown the potential to generate PET images from non-corrected PET images. Our aim in this work is to develop a CT-free correction for a long axial FOV PET scanner. METHODS: Whole body PET images of 165 patients scanned with a digital regular FOV PET scanner (Biograph Vision 600 (Siemens Healthineers) in Shanghai and Bern) was included for the development and testing of the deep learning methods. Furthermore, the developed algorithm was tested on data of 7 patients scanned with a long axial FOV scanner (Biograph Vision Quadra, Siemens Healthineers). A 2D generative adversarial network (GAN) was developed featuring a residual dense block, which enables the model to fully exploit hierarchical features from all network layers. The normalized root mean squared error (NRMSE) and peak signal-to-noise ratio (PSNR), were calculated to evaluate the results generated by deep learning. RESULTS: The preliminary results showed that, the developed deep learning method achieved an average NRMSE of 0.4±0.3% and PSNR of 51.4±6.4 for the test on Biograph Vision, and an average NRMSE of 0.5±0.4% and PSNR of 47.9±9.4 for the validation on Biograph Vision Quadra, after applied transfer learning. CONCLUSION: The developed deep learning method shows the potential for CT-free AI-correction for a long axial FOV PET scanner. Work in progress includes clinical assessment of PET images by independent nuclear medicine physicians. Training and fine-tuning with more datasets will be performed to further consolidate the development.

Feasibility of late acquisition [68Ga]Ga-PSMA-11 PET/CT using a long axial field-of-view PET/CT scanner for the diagnosis of recurrent prostate cancer-first clinical experiences.

PURPOSE: While acquisition of images in [68 Ga]Ga-PSMA-11 following longer uptake times can improve lesion uptake and contrast, resultant imaging quality and count statistics are limited by the isotope's half-life (68 min). Here, we present a series of cases demonstrating that when performed using a long axial field-of-view (LAFOV) PET/CT system, late imaging is feasible and can even provide improved image quality compared to regular acquisitions. METHODS: In this retrospective case series, we report our initial experiences with 10 patients who underwent standard imaging at 1 h p.i. following administration of 192 ± 36 MBq [68 Ga]Ga-PSMA-11 with additional late imaging performed at 4 h p.i. Images were acquired in a single bed position for 6 min at 1 h p.i. and 16 min p.i. at 4 h p.i. using a LAFOV scanner (106 cm axial FOV). Two experienced nuclear medicine physicians reviewed all scans in consensus and evaluated overall image quality (5-point Likert scale), lesion uptake in terms of standardised uptake values (SUV), tumour to background ratio (TBR) and target-lesion signal to background noise (SNR). RESULTS: Subjective image quality as rated on a 5-point Likert scale was only modestly lower for late acquisitions (4.2/5 at 4 h p.i.; 5/5 1 h p.i.), TBR was significantly improved (4 h: 3.41 vs 1 h: 1.93, p < 0.001) and SNR was improved with borderline significance (4 h: 33.02 vs 1 h: 24.80, p = 0.062) at later imaging. Images were obtained with total acquisition times comparable to routine examinations on standard axial FOV scanners. CONCLUSION: Late acquisition in tandem with a LAFOV PET/CT resulted in improvements in TBR and SNR and was associated with only modest impairment in subjective visual imaging quality. These data show that later acquisition times for [68 Ga]Ga-PSMA-11 may be preferable when performed on LAFOV systems.

Clinical performance of long axial field of view PET/CT: a head-to-head intra-individual comparison of the Biograph Vision Quadra with the Biograph Vision PET/CT.

PURPOSE: To investigate the performance of the new long axial field-of-view (LAFOV) Biograph Vision Quadra PET/CT and a standard axial field-of-view (SAFOV) Biograph Vision 600 PET/CT (both: Siemens Healthineers) system using an intra-patient comparison. METHODS: Forty-four patients undergoing routine oncological PET/CT were prospectively included and underwent a same-day dual-scanning protocol following a single administration of either 18F-FDG (n = 20), 18F-PSMA-1007 (n = 16) or 68Ga-DOTA-TOC (n = 8). Half the patients first received a clinically routine examination on the SAFOV (FOVaxial 26.3 cm) in continuous bed motion and then immediately afterwards on the LAFOV system (10-min acquisition in list mode, FOVaxial 106 cm); the second half underwent scanning in the reverse order. Comparisons between the LAFOV at different emulated scan times (by rebinning list mode data) and the SAFOV were made for target lesion integral activity, signal to noise (SNR), target lesion to background ratio (TBR) and visual image quality. RESULTS: Equivalent target lesion integral activity to the SAFOV acquisitions (16-min duration for a 106 cm FOV) were obtained on the LAFOV in 1.63 ± 0.19 min (mean ± standard error). Equivalent SNR was obtained by 1.82 ± 1.00 min LAFOV acquisitions. No statistically significant differences (p > 0.05) in TBR were observed even for 0.5 min LAFOV examinations. Subjective image quality rated by two physicians confirmed the 10 min LAFOV to be of the highest quality, with equivalence between the LAFOV and the SAFOV at 1.8 ± 0.85 min. By analogy, if the LAFOV scans were maintained at 10 min, proportional reductions in applied radiopharmaceutical could obtain equivalent lesion integral activity for activities under 40 MBq and equivalent doses for the PET component of <1 mSv. CONCLUSION: Improved image quality, lesion quantification and SNR resulting from higher sensitivity were demonstrated for an LAFOV system in a head-to-head comparison under clinical conditions. The LAFOV system could deliver images of comparable quality and lesion quantification in under 2 min, compared to routine SAFOV acquisition (16 min for equivalent FOV coverage). Alternatively, the LAFOV system could allow for low-dose examination protocols. Shorter LAFOV acquisitions (0.5 min), while of lower visual quality and SNR, were of adequate quality with respect to target lesion identification, suggesting that ultra-fast or low-dose acquisitions can be acceptable in selected settings.

Digital PET/CT allows for shorter acquisition protocols or reduced radiopharmaceutical dose in [18F]-FDG PET/CT.

PURPOSE: To establish the feasibility of shorter acquisition times (and by analogy, applied activity) on tumour detection and lesion contrast in digital PET/CT. METHODS: Twenty-one randomly selected patients who underwent oncological [18F]-FDG PET/CT on a digital PET/CT were retrospectively evaluated. Scan data were anonymously obtained and reconstructed in list-mode acquisition for a standard 2 min/bed position (bp), 1 min/bp and 30 s/bp (100%, 50% and 25% time or applied activity, respectively). Scans were randomized and read by two nuclear medicine physicians in a consensus read. Readers were blind to clinical details. Scans were evaluated for the number of pathological lesions detected. Measured uptake for lesions was evaluated by maximum and mean standardized uptake value (SUVmax and SUVmean, respectively) and tumour-to-backround ratio (TBR) were compared. Agreement between the three acquisitions was compared by Krippendorf's alpha. RESULTS: Overall n = 100 lesions were identified in the 2 min and 1 min/bp acquisitions and n = 98 lesions in the 30 s/bp acquisitions. Agreement between the three acquisitions with respect to lesion number and tumour-to-background ratio showed almost perfect agreement (K's α = 0.999). SUVmax, SUVmean and TBR likewise showed > 98% agreement, with longer acquisitions being associated with slightly higher mean TBR (2 min/bp 7.94 ± 4.41 versus 30 s/bp 7.84 ± 4.22, p < 0.05). CONCLUSION: Shorter acquisition times have traditionally been associated with reduced lesion detectability or the requirement for larger amounts of radiotracer activity. These data confirm that this is not the case for new-generation digital PET scanners, where the known higher sensitivity results in clinically adequate images for shorter acquisitions. Only a small variation in the semi-quantitative parameters SUVmax, SUVmean and TBR was seen, confirming that either reduction of acquisition time or (by analogy) applied activity can be reduced as much as 75% in digital PET/CT without apparent clinical detriment.