Quantitative assessment of kidney split function and mean transit time in healthy patients using dynamic 18F-FDG PET/MRI studies with denoising and deconvolution methods making use of Legendre polynomials.

[en] PURPOSE: Our objective was to assess a deconvolution and denoising technique based on Legendre polynomials compared to matrix deconvolution on dynamic 18F-FDG renography of healthy patients.
METHOD: The study was carried out and compared to the data of 24 healthy patients from a published study who underwent examinations with 99mTc-MAG3 planar scintigraphy and 18F-FDG PET/MRI. Due to corruption issues in some data used in the published article, post-publication measurements were provided. We have been warned that post-publication data were treated differently. The smoothing method switched from Bezier to Savitzky-Golay and the deconvolution from matrix-based (with Tikhonov Regularization) to Richardson-Lucy. A comparison of the split function and mean transit times of the published and post-publication data against our method based on Legendre polynomials was performed.
RESULTS: For split function, we only observed a good agreement between the processing methods for the 99mTc-MAG3 and the post-published data. No correlation was found between the split functions obtained on the 99mTc-MAG3 and the 18F-FDG, contrary to the published study. However, all calculated split function values for 18F-FDG and 99mTc-MAG3 were within the established normal range. For the mean transit time, the correlation was moderate with published data and very good with the post-publication measurements for both 99mTc-MAG3 and 18F-FDG. Bias of the Bland-Altman analysis of the mean transit times for 99mTc-MAG3 versus 18F-FDG was 1.1 min (SD 1.7 min) for the published data, - 0.11 min (SD 1.9 min) for the post-publication results and .05 min (SD 1.9 min) for our method.
CONCLUSIONS: The processing methods used in the original publication and in the post-publication work were quite complex and required adaptation of the fitting parameters for each individual and each type of examination. Our method did not require any specific adjustment; the same unmodified and fully automated algorithm was successfully applied to all data.