Development and Validation of a Semi-Automated, Preclinical, MRI-Template Based PET Image Data Analysis Tool for Rodents

Aim In PET imaging, the different types of radiotracers and accumulations, as well as the diversity of disease patterns, make the analysis of molecular imaging data acquired in vivo challenging. Here, we evaluate and validate a semi-automated MRI template-based data analysis tool that allows preclinical PET images to be aligned to a self-created PET template. Based on the user-defined volume-of-interest (VOI), image data can then be evaluated using three different semi-quantitative parameters: normalized activity, standardized uptake value, and uptake ratio. Materials and Methods The nuclear medicine Data Processing Analysis tool (NU_DPA) was implemented in Matlab. Testing and validation of the tool was performed using two types of radiotracers in different kinds of stroke-related brain diseases in rat models. The radiotracers used are 2-[F-18]fluoro-2-deoxyglucose ([F-18]FDG), a metabolic tracer with symmetrical distribution in brain, and [Ga-68]Ga-Fucoidan, a target-selective radioligand specifically binding to p-selectin. After manual image import, the NU_DPA tool automatically creates an averaged PET template out of the acquired PET images, to which all PET images are then aligned onto. The added MRI template-based information, resized to the lower PET resolution, defines the VOI and also allows a precise subdivision of the VOI into individual sub-regions. The aligned PET images can then be evaluated semi-quantitatively for all regions defined in the MRI atlas. In addition, a statistical analysis and evaluation of the semi-quantitative parameters can then be performed in the NU_DPA tool. Results Using ischemic stroke data in Wistar rats as an example, the statistical analysis of the tool should be demonstrated. In this [F-18]FDG-PET experiment, three different experimental states were compared: healthy control state, ischemic stroke without electrical stimulation, ischemic stroke with electrical stimulation. Thereby, statistical data evaluation using the NU_DPA tool showed that the glucose metabolism in a photothrombotic lesion can be influenced by electrical stimulation. Conclusion Our NU_DPA tool allows a very flexible data evaluation of small animal PET data in vivo including statistical data evaluation. Using the radiotracers [F-18]FDG and [Ga-68]Ga-Fucoidan, it was shown that the semi-automatic MRI-template based data analysis of the NU_DPA tool is potentially suitable for both metabolic radiotracers as well as target-selective radiotracers.