TY - JOUR A1 - Leube, Julian A1 - Gustafsson, Johan A1 - Lassmann, Michael A1 - Salas-Ramirez, Maikol A1 - Tran-Gia, Johannes T1 - Analysis of a deep learning-based method for generation of SPECT projections based on a large Monte Carlo simulated dataset JF - EJNMMI Physics N2 - Background In recent years, a lot of effort has been put in the enhancement of medical imaging using artificial intelligence. However, limited patient data in combination with the unavailability of a ground truth often pose a challenge to a systematic validation of such methodologies. The goal of this work was to investigate a recently proposed method for an artificial intelligence-based generation of synthetic SPECT projections, for acceleration of the image acquisition process based on a large dataset of realistic SPECT simulations. Methods A database of 10,000 SPECT projection datasets of heterogeneous activity distributions of randomly placed random shapes was simulated for a clinical SPECT/CT system using the SIMIND Monte Carlo program. Synthetic projections at fixed angular increments from a set of input projections at evenly distributed angles were generated by different u-shaped convolutional neural networks (u-nets). These u-nets differed in noise realization used for the training data, number of input projections, projection angle increment, and number of training/validation datasets. Synthetic projections were generated for 500 test projection datasets for each u-net, and a quantitative analysis was performed using statistical hypothesis tests based on structural similarity index measure and normalized root-mean-squared error. Additional simulations with varying detector orbits were performed on a subset of the dataset to study the effect of the detector orbit on the performance of the methodology. For verification of the results, the u-nets were applied to Jaszczak and NEMA physical phantom data obtained on a clinical SPECT/CT system. Results No statistically significant differences were observed between u-nets trained with different noise realizations. In contrast, a statistically significant deterioration was found for training with a small subset (400 datasets) of the 10,000 simulated projection datasets in comparison with using a large subset (9500 datasets) for training. A good agreement between synthetic (i.e., u-net generated) and simulated projections before adding noise demonstrates a denoising effect. Finally, the physical phantom measurements show that our findings also apply for projections measured on a clinical SPECT/CT system. Conclusion Our study shows the large potential of u-nets for accelerating SPECT/CT imaging. In addition, our analysis numerically reveals a denoising effect when generating synthetic projections with a u-net. Clinically interesting, the methodology has proven robust against camera orbit deviations in a clinically realistic range. Lastly, we found that a small number of training samples (e.g., ~ 400 datasets) may not be sufficient for reliable generalization of the u-net. KW - 177Lu KW - Monte Carlo KW - SPECT KW - Deep learning KW - Denoising Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-300697 SN - 2197-7364 VL - 9 ER - TY - JOUR A1 - Werner, Rudolf A. A1 - Beykan, Seval A1 - Higuchi, Takahiro A1 - Lückerath, Katharina A1 - Weich, Alexander A1 - Scheurlen, Michael A1 - Bluemel, Christina A1 - Herrmann, Ken A1 - Buck, Andreas K. A1 - Lassmann, Michael A1 - Lapa, Constantin A1 - Hänscheid, Heribert T1 - The impact of \(^{177}\)Lu-octreotide therapy on \(^{99m}\)Tc-MAG3 clearance is not predictive for late nephropathy JF - Oncotarget N2 - Peptide Receptor Radionuclide Therapy (PRRT) for the treatment of neuroendocrine tumors may lead to kidney deterioration. This study aimed to evaluate the suitability of \(^{99m}\)Tc-mercaptoacetyltriglycine (\(^{99m}\)Tc-MAG3) clearance for the early detection of PRRT-induced changes on tubular extraction (TE). TE rate (TER) was measured prior to 128 PRRT cycles (7.6±0.4 GBq \(^{177}\)Lu-octreotate/octreotide each) in 32 patients. TER reduction during PRRT was corrected for age-related decrease and analyzed for the potential to predict loss of glomerular filtration (GF). The GF rate (GFR) as measure for renal function was derived from serum creatinine. The mean TER was 234 ± 53 ml/min/1.73 m² before PRRT (baseline) and 221 ± 45 ml/min/1.73 m² after a median follow-up of 370 days. The age-corrected decrease (mean: -3%, range: -27% to +19%) did not reach significance (p=0.09) but significantly correlated with the baseline TER (Spearman p=-0.62, p<0.001). Patients with low baseline TER showed an improved TER after PRRT, high decreases were only observed in individuals with high baseline TER. Pre-therapeutic TER data were inferior to plasma creatinine-derived GFR estimates in predicting late nephropathy. TER assessed by \(^{99m}\)Tc-MAG3­clearance prior to and during PRRT is not suitable as early predictor of renal injury and an increased risk for late nephropathy. KW - renal scintigraphy KW - neuroendocrine tumor KW - 177Lu KW - MAG3 KW - PRRT Y1 - 2016 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-177318 VL - 7 IS - 27 ER -