Longitudinal mouse-PET imaging: a reliable method for estimating binding parameters without a reference region or blood sampling

Abstract

Longitudinal mouse PET imaging is becoming increasingly popular due to the large number of transgenic and disease models available but faces challenges. These challenges are related to the small size of the mouse brain and the limited spatial resolution of microPET scanners, along with the small blood volume making arterial blood sampling challenging and impossible for longitudinal studies. The ability to extract an input function directly from the image would be useful for quantification in longitudinal small animal studies where there is no true reference region available such as TSPO imaging.

Methods: Using dynamic, whole-body ¹⁸F-DPA-714 PET scans (60 min) in a mouse model of hippocampal sclerosis, we applied a factor analysis (FA) approach to extract an image-derived input function (IDIF). This mouse-specific IDIF was then used for 4D-resolution recovery and denoising (4D-RRD) that outputs a dynamic image with better spatial resolution and noise properties, and a map of the total volume of distribution (V_T) was obtained using a basis function approach in a total of 9 mice with 4 longitudinal PET scans each. We also calculated percent injected dose (%ID) with and without 4D-RRD. The V_T and %ID parameters were compared to quantified ex vivo autoradiography using regional correlations of the specific binding from autoradiography against V_T and %ID parameters.

Results: The peaks of the IDIFs were strongly correlated with the injected dose (Pearson R = 0.79). The regional correlations between the %ID estimates and autoradiography were R = 0.53 without 4D-RRD and 0.72 with 4D-RRD over all mice and scans. The regional correlations between the V_T estimates and autoradiography were R = 0.66 without 4D-RRD and 0.79 with application of 4D-RRD over all mice and scans.

Conclusion: We present a FA approach for IDIF extraction which is robust, reproducible and can be used in quantification methods for resolution recovery, denoising and parameter estimation. We demonstrated that the proposed quantification method yields parameter estimates closer to ex vivo measurements than semi-quantitative methods such as %ID and is immune to tracer binding in tissue unlike reference tissue methods. This approach allows for accurate quantification in longitudinal PET studies in mice while avoiding repeated blood sampling.

Keywords: Factor analysis; Image-derived input function; Mouse; PET; TSPO.

Fig. 1

Process for extracting the IDIF from the dynamic PET scan: (1) the whole-body dynamic PET captures all activity; (2) FA is run with 3 (presaturation) or 4 (tracer dose) factors – the factor curves are shown along with their corresponding spatial distribution and relative intensity. The curve with the earliest peak (in red) shows the strongest signal in the expected regions for blood (tail vein, aorta, lungs); (3) all factors are summed together; (4) the whole-body TAC is obtained from a ROI placed around the whole body, and the total activity in Bq is calculated from the measured activity concentration (Bq/cc) multiplied by ROI volume; (5) the ratio between the summed factors and the whole-body TAC is calculated and the average of the ratio from 10 min onwards is calculated; (6) the blood factor curve is normalized to Bq using the average ratio value. This IDIF is then metabolite corrected and used in the image processing and parameter estimation

Fig. 2

a Mean IDIF extracted from the presaturation studies, with fit and residuals underneath. b Mean and standard deviation of extracted IDIFs, fitted and metabolite corrected for the four time points with the peak inlaid

Fig. 3

Regional parameter estimates for each time point post kainic acid injection (mean and standard deviation). Top, Autoradiography (cpm/mm²) (n = 3 at each time point); Middle, %ID without 4D-RRD; Bottom, PET V_T after 10 iterations of 4D-RRD

Fig. 4

Pearson R coefficients between [³H]-DPA714 autoradiography and PET measures for each time point post kainic acid injection. The coefficients between the autoradiography and %ID or V_T are shown for original images and after 4D-RRD processing. The stars represent the significance level of the Pearson R coefficient (*p < 0.05, **p < 0.01, ***p < 0.001)

Fig. 5

Average parametric maps for each time point post kainic acid (baseline, 7 days, 1 month and 6 months). The images are for %ID (dark grey segment) and V_T (light grey segment) at a ventral (top images) and dorsal (bottom images) hippocampal slice. The bottom segment (white) shows the [³H]DPA-714 autoradiography at the same time points for the same slices for one representative animal