Can a Deep Progressive Learning Method Help to Achieve High Image Quality as Total-body PET Imaging?

Purpose To propose and validate a total-body PET (TB-PET) guided deep progressive learning method (DPR) for low-dose clinical imaging of standard axial field-of-view PET/CT scanner (SAFOV-PET).Methods List-mode raw data from a total of 182 scans were collected, including 100 patient scans from a TB-PET, and 15 phantom and 67 patient scans from a SAFOV-PET. Neural networks employed in DPR were trained with the high-quality images obtained from the TB-PET using a progressive learning strategy and evaluated on a SAFOV-PET through three stages of studies. The CTN phantom was firstly used to verify the effectiveness of protocols in DPR and OSEM algorithms. Subsequently, list-mode rawdata from retrospective and prospective PET oncological patients (n=26 and 41, respectively) were rebinned into short duration scans (referred as to DPR_full, DPR_1/2, DPR_1/3, and DPR_1/4), and reconstructed with DPR. Full-duration data were reconstructed with OSEM to generate images as a reference. In the retrospective study, the image quality was evaluated using the metrics of standard uptake value (SUV) and target-to-liver ratio (TLR) in lesions, and coefficient of variation (COV) in the liver, which provided evidence for the subsequent study with real-world low-dose injection. In the prospective study, the quantification accuracy was evaluated with the agreement of SUVs in the liver, the blood pool, and the muscle between the DPR and the OSEM images. Quantitative analysis was also performed with the SUV and the TLR in lesions, furthermore on small lesions with a diameter no more than 10mm. In addition, qualitative analysis was performed using a 5-point Likert scale on the following perspectives: contrast, noise, and diagnostic confidence. Results The protocols used in the study were verified to meet the EANM EARL2 requirements. In the retrospective study, the DPR group with one-third acquisition time can yield a comparable image quality to the reference. In the prospective study, good agreement of the SUVs between DPR and OSEM was found in all the selected background tissues even if the injected dose was reduced to 1/3. Both quantitative and qualitative results demonstrated that the DPR_1/3 group showed no significant difference with the reference regarding the liver COV and subjective scores. The lesion SUVs and TLRs in the DPR_1/3 group were significantly enhanced compared with the reference, even for small lesions. Conclusions The proposed DPR method can reduce the injected dose of SAFOV-PET scan by up to 2/3 in a real-world deployment while maintaining image quality.

The Number of Frames on ECG-Gated 18F-FDG Small Animal PET Has a Significant Impact on LV Systolic and Diastolic Functional Parameters

Objectives. This study is aimed at investigating the impact of frame numbers in preclinical electrocardiogram- (ECG-) gated 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) on systolic and diastolic left ventricular (LV) parameters in rats. Methods. 18F-FDG PET imaging using a dedicated small animal PET system with list mode data acquisition and continuous ECG recording was performed in diabetic and control rats. The list-mode data was sorted and reconstructed with different numbers of frames (4, 8, 12, and 16) per cardiac cycle into tomographic images. Using an automatic ventricular edge detection software, left ventricular (LV) functional parameters, including ejection fraction (EF), end-diastolic (EDV), and end-systolic volume (ESV), were calculated. Diastolic variables (time to peak filling (TPF), first third mean filling rate (1/3 FR), and peak filling rate (PFR)) were also assessed. Results. Significant differences in multiple parameters were observed among the reconstructions with different frames per cardiac cycle. EDV significantly increased by numbers of frames (353.8 ± 57.7 μl ∗ , 380.8 ± 57.2 μl ∗ , 398.0 ± 63.1 μl ∗ , and 444.8 ± 75.3 μl at 4, 8, 12, and 16 frames, respectively; ∗ P < 0.0001 vs. 16 frames), while systolic (EF) and diastolic (TPF, 1/3 FR and PFR) parameters were not significantly different between 12 and 16 frames. In addition, significant differences between diabetic and control animals in 1/3 FR and PFR in 16 frames per cardiac cycle were observed ( P < 0.005 ), but not for 4, 8, and 12 frames. Conclusions. Using ECG-gated PET in rats, measurements of cardiac function are significantly affected by the frames per cardiac cycle. Therefore, if you are going to compare those functional parameters, a consistent number of frames should be used.

Deep learning–based denoising of low-dose SPECT myocardial perfusion images: quantitative assessment and clinical performance

Purpose This work was set out to investigate the feasibility of dose reduction in SPECT myocardial perfusion imaging (MPI) without sacrificing diagnostic accuracy. A deep learning approach was proposed to synthesize full-dose images from the corresponding low-dose images at different dose reduction levels in the projection space. Methods Clinical SPECT-MPI images of 345 patients acquired on a dedicated cardiac SPECT camera in list-mode format were retrospectively employed to predict standard-dose from low-dose images at half-, quarter-, and one-eighth-dose levels. To simulate realistic low-dose projections, 50%, 25%, and 12.5% of the events were randomly selected from the list-mode data through applying binomial subsampling. A generative adversarial network was implemented to predict non-gated standard-dose SPECT images in the projection space at the different dose reduction levels. Well-established metrics, including peak signal-to-noise ratio (PSNR), root mean square error (RMSE), and structural similarity index metrics (SSIM) in addition to Pearson correlation coefficient analysis and clinical parameters derived from Cedars-Sinai software were used to quantitatively assess the predicted standard-dose images. For clinical evaluation, the quality of the predicted standard-dose images was evaluated by a nuclear medicine specialist using a seven-point (− 3 to + 3) grading scheme. Results The highest PSNR (42.49 ± 2.37) and SSIM (0.99 ± 0.01) and the lowest RMSE (1.99 ± 0.63) were achieved at a half-dose level. Pearson correlation coefficients were 0.997 ± 0.001, 0.994 ± 0.003, and 0.987 ± 0.004 for the predicted standard-dose images at half-, quarter-, and one-eighth-dose levels, respectively. Using the standard-dose images as reference, the Bland–Altman plots sketched for the Cedars-Sinai selected parameters exhibited remarkably less bias and variance in the predicted standard-dose images compared with the low-dose images at all reduced dose levels. Overall, considering the clinical assessment performed by a nuclear medicine specialist, 100%, 80%, and 11% of the predicted standard-dose images were clinically acceptable at half-, quarter-, and one-eighth-dose levels, respectively. Conclusion The noise was effectively suppressed by the proposed network, and the predicted standard-dose images were comparable to reference standard-dose images at half- and quarter-dose levels. However, recovery of the underlying signals/information in low-dose images beyond a quarter of the standard dose would not be feasible (due to very poor signal-to-noise ratio) which will adversely affect the clinical interpretation of the resulting images.

Fast Energy Dependent Scatter Correction for List-Mode PET Data

Improvements in energy resolution of modern positron emission tomography (PET) detectors have created opportunities to implement energy-based scatter correction algorithms. Here, we use the energy information of auxiliary windows to estimate the scatter component. Our method is directly implemented in an iterative reconstruction algorithm, generating a scatter-corrected image without the need for sinograms. The purpose was to implement a fast energy-based scatter correction method on list-mode PET data, when it was not possible to use an attenuation map as a practical approach for the scatter degradation. The proposed method was evaluated using Monte Carlo simulations of various digital phantoms. It accurately estimated the scatter fraction distribution, and improved the image contrast in the simulated studied cases. We conclude that the proposed scatter correction method could effectively correct the scattered events, including multiple scatters and those originated in sources outside the field of view.

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.