18FDG PET/CT and Machine Learning for the prediction of lung cancer response to immunotherapy

Hugo Schmutz (1, 2, 3) , Pierre-Alexandre Mattei (1, 4, 2) , Sara Contu (5) , David Chardin (5) , Olivier Humbert (5)

1 MAASAI - Modèles et algorithmes pour l’intelligence artificielle
2 UniCA - Université Côte d'Azur
3 TIRO-MATOs UMR E4320 - Transporteurs et Imagerie, Radiothérapie en Oncologie et Mécanismes biologiques des Altérations du Tissu Osseux
4 LJAD - Laboratoire Jean Alexandre Dieudonné
5 UNICANCER/CAL - Centre de Lutte contre le Cancer Antoine Lacassagne [Nice]

In patients with non-small cell lung cancer (NSCLC) treated with immunotherapy, individual biological and PET imaging prognostic biomarkers have been recently identified. However, combination of biomarkers has not been studied yet. The purpose of this study is to combine clinical, biological and 18FDG PET/CT parameters and use machine-learning algorithms to build more accurate prognostic models of NSCLC response to immunotherapy

Domaines: Informatique [cs]; Sciences du Vivant [q-bio]

Hugo Schmutz, Pierre-Alexandre Mattei, Sara Contu, David Chardin, Olivier Humbert. 18FDG PET/CT and Machine Learning for the prediction of lung cancer response to immunotherapy. EANM 2022 - 35th Annual Congres - Annual Congress of the European Association of Nuclear Medicine, Oct 2022, Barcelona, Spain. pp.245, ⟨10.1007/s00259-022-05924-4⟩. ⟨hal-03876074⟩