Positron emission tomography and single photon emission computed tomography imaging of tertiary lymphoid structures during the development of lupus nephritis.

Lymphoid neogenesis occurs in tissues targeted by chronic inflammatory processes, such as infection and autoimmunity. In systemic lupus erythematosus (SLE), such structures develop within the kidneys of lupus-prone mice ((NZBXNZW)F1) and are observed in kidney biopsies taken from SLE patients with lupus nephritis (LN). The purpose of this prospective longitudinal animal study was to detect early kidney changes and tertiary lymphoid structures (TLS) using in vivo imaging. Positron emission tomography (PET) by tail vein injection of 18-F-fluoro-2-deoxy-D-glucose (18F-FDG)(PET/FDG) combined with computed tomography (CT) for anatomical localization and single photon emission computed tomography (SPECT) by intraperitoneal injection of 99mTC labeled Albumin Nanocoll (99mTC-Nanocoll) were performed on different disease stages of NZB/W mice (n = 40) and on aged matched control mice (BALB/c) (n = 20). By using one-way ANOVA analyses, we compared two different compartmental models for the quantitative measure of 18F-FDG uptake within the kidneys. Using a new five-compartment model, we observed that glomerular filtration of 18FFDG in lupus-prone mice decreased significantly by disease progression measured by anti-dsDNA Ab production and before onset of proteinuria. We could not visualize TLS within the kidneys, but we were able to visualize pancreatic TLS using 99mTC Nanocoll SPECT. Based on our findings, we conclude that the five-compartment model can be used to measure changes of FDG uptake within the kidney. However, new optimal PET/SPECT tracer administration sites together with more specific tracers in combination with magnetic resonance imaging (MRI) may make it possible to detect formation of TLS and LN before clinical manifestations.

Machine learning derived input-function in a dynamic 18F-FDG PET study of mice.

Tracer kinetic modelling, based on dynamic 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) is used to quantify glucose metabolism in humans and animals. Knowledge of the arterial input-function (AIF) is required for such measurements. Our aim was to explore two non-invasive machine learning-based models, for AIF prediction in a small-animal dynamic FDG PET study. 7 tissue regions were delineated in images from 68 FDG PET/computed tomography mouse scans. Two machine learning-based models were trained for AIF prediction, based on Gaussian processes (GP) and a long short-term memory (LSTM) recurrent neural network, respectively. Because blood data were unavailable, a reference AIF was formed by fitting an established AIF model to vena cava and left ventricle image data. The predicted and reference AIFs were compared by the area under curve (AUC) and root mean square error (RMSE). Net-influx rate constants, K i , were calculated with a two-tissue compartment model, using both predicted and reference AIFs for three tissue regions in each mouse scan, and compared by means of error, ratio, correlation coefficient, P value and Bland-Altman analysis. The impact of different tissue regions on AIF prediction was evaluated by training a GP and an LSTM model on subsets of tissue regions, and calculating the RMSE between the reference and the predicted AIF curve. Both models generated AIFs with AUCs similar to reference. The LSTM models resulted in lower AIF RMSE, compared to GP. K i from both models agreed well with reference values, with no significant differences. Myocardium was highlighted as important for AIF prediction, but AIFs with similar RMSE were obtained also without myocardium in the input data. Machine learning can be used for accurate and non-invasive prediction of an image-derived reference AIF in FDG studies of mice. We recommend the LSTM approach, as this model predicts AIFs with lower errors, compared to GP.