Simulated data are of foremost importance for the development of PET imaging processing methods, especially computer aided diagnosis (CAD) systems based on statistical decision theory. Such data indeed allow building large and well referenced databases for the training phase of such systems. This however implies to perform realistic simulations of accurate biological radioactive distribution in a reasonable computation time.
The oncoPET_DB database was designed to meet this goal [TOME-10].
A full description of this database is available here.
OncoPET_DB provides 100 realistic simulated [18F]FDG PET images with (50 cases) or without (50 cases) inserted lesions. As far as we know, this database was the first addressing the need of simulated [18F]FDG PET oncology images by providing a series of whole-body (WB) patient images with well controlled inserted lesions of calibrated uptakes.
The OncoPET_respi database was designed in a second phase to include both anatomical variability and respiratory motion [LEMA-09] [MARA-11]
under construction