Purpose: Early deep-learning-based image denoising techniques mainly focused on a fully supervised model that learns how to generate a clean image from the noisy input (noise2clean: N2C). The aim of this study is to explore the feasibility of the self-supervised methods (noise2noise: N2N and noiser2noise: Nr2N) for PET image denoising based on the measured PET data sets by comparing their performance with the conventional N2C model. Methods: For training and evaluating the networks, 18F-FDG brain PET/CT scan data of 14 patients was retrospectively used (10 for training and 4 for testing). From the 60-min list-mode data, we generated a total of 100 data bins with 10-s duration. We also generated 40-s-long data by adding four non-overlapping 10-s bins and 300-s-long reference data by adding all list-mode data. We employed U-Net that is widely used for various tasks in biomedical imaging to train and test proposed denoising models. Results: All the N2C, N2N, and Nr2N were effective for improving the noisy inputs. While N2N showed equivalent PSNR to the N2C in all the noise levels, Nr2N yielded higher SSIM than N2N. N2N yielded denoised images similar to reference image with Gaussian filtering regardless of input noise level. Image contrast was better in the N2N results. Conclusion The self-supervised denoising method will be useful for reducing the PET scan time or radiation dose.

Background: Coronavirus disease 2019 (COVID-19) has become a global pandemic, which prompts a consensus for the necessity to seek risk factors for this critical disease. Risk factors affecting mortality of the disease remain elusive. Diabetes and hyperglycemia are known to negatively affect a host’s antiviral immunity. We evaluated the relationship between a history of diabetes, fasting plasma glucose (FPG) levels and mortality among severely ill patients with COVID-19. Methods: This was a retrospective cohort study that assessed 106 adult inpatients (aged ≥18 years) from two tertiary hospitals in Daegu, South Korea. The participants were transferred to tertiary hospitals because their medical condition required immediate intensive care. The demographic and laboratory data were compared between COVID-19 patients who survived and those who did not. Results: Compared with the survivor group, age, and the proportions of diabetes, chronic lung disease and FPG were significantly higher in the deceased group. In the Cox proportional hazards regression model for survival analysis, FPG level and age were identified as significant predictors of mortality (P<0.05). The threshold values for predicting high mortality were age >68 years and FPG of 168 mg/dL, respectively. Among those without diabetes, high FPG remained a significant predictor of mortality (P<0.04). Conclusion High FPG levels significantly predicted mortality in COVID-19, regardless of a known history of diabetes. These results suggest intensive monitoring should be provided to COVID-19 patients who have a high FPG level.

Purpose: Since accurate lung cancer segmentation is required to determine the functional volume of a tumor in [ 18 F]FDG PET/CT, we propose a two-stage U-Net architecture to enhance the performance of lung cancer segmentation using [ 18 F]FDG PET/CT. Methods: The whole-body [ 18 F]FDG PET/CT scan data of 887 patients with lung cancer were retrospectively used for network training and evaluation. The ground-truth tumor volume of interest was drawn using the LifeX software. The dataset was randomly partitioned into training, validation, and test sets. Among the 887 PET/CT and VOI datasets, 730 were used to train the proposed models, 81 were used as the validation set, and the remaining 76 were used to evaluate the model. In Stage 1, the global U-net receives 3D PET/CT volume as input and extracts the preliminary tumor area, generating a 3D binary volume as output. In Stage 2, the regional U-net receives eight consecutive PET/CT slices around the slice selected by the Global U-net in Stage 1 and generates a 2D binary image as the output. Results: The proposed two-stage U-Net architecture outperformed the conventional one-stage 3D U-Net in primary lung cancer segmentation. The two-stage U-Net model successfully predicted the detailed margin of the tumors, which was determined by manually drawing spherical VOIs and applying an adaptive threshold. Quantitative analysis using the Dice similarity coefficient confirmed the advantages of the two-stage U-Net. Conclusion The proposed method will be useful for reducing the time and effort required for accurate lung cancer segmentation in [ 18 F]FDG PET/CT.