Neuroendocrine neoplasms (NENs) are a heterogeneous group of malignancies which arise from neuroendocrine cells and are divided into well-differentiated neuroendocrine tumors (NETs) and poorly differentiated neuroendocrine carcinomas (NECs). Currently, 18F-FDG-PET is the preferred choice for NECs, whereas 68Ga-DOTA-peptides PET is useful for the characterization of NETs.

The potential of radiomics has already been demonstrated in 18F-FDG-PET, but this is currently lacking for 68Ga-DOTA-peptides PET images. This research line is focused on the development of an accurate and robust segmentation algorithm for NETs and the exploration of potentials and pitfalls associated with a radiomics model on 68Ga-DOTA-TOC PET/CT images.


  • Filippo Molinari (Full Professor)
  • Bruno De Santi (PhD Student)

  • Recent publications:

  • Diagnostic Value of Conventional PET Parameters and Radiomic Features Extracted from 18F-FDG-PET/CT for Histologic Subtype Classification and Characterization of Lung Neuroendocrine Neoplasms
      Philippe Thuillier,Virginia Liberini,Osvaldo Rampado, Elena Gallio,Bruno De Santi, Francesco Ceci, Jasna Metovic, Mauro Papotti, Marco Volante, Filippo Molinari, Désirée Deandreis
  • Impact of segmentation and discretization on radiomic features in 68Ga-DOTA-TOC PET/CT images of neuroendocrine tumor
      Virginia Liberini, Bruno De Santi, Osvaldo Rampado, Elena Gallio, Beatrice Dionisi, Francesco Ceci, Giulia Polverari, Philippe Thuillier, Filippo Molinari & Désirée Deandreis
      European Journal of Nuclear Medicine and Molecular Imaging Physics