Machine learning in the histological differentiation of mediastinal bulky lymphoma with radiomic $^{18}F$-FDG PET/CT features.

Barbetti M., Abenavoli E., Anderlini L., Berti V., Nassi L., Puccini B., Romano I., Santi R., Talamonti C.
  Mercoledì 14/09   13:30 - 18:30   Aula E - Rosalind Franklin   V - Biofisica e fisica medica   Presentazione
One of the most common forms of hematologic cancers is mediastinal bulky lymphoma (MBL). It can be characterized using both morphological and functional imaging which represents one of the fundamental diagnostic tools available. A histological mediastinal lymphomas model is fundamental to offer solutions tailored to the single patient moving toward "personalized medicine", where Machine Learning (ML) can make the difference and bring a significant contribution to the whole process. This study makes use of Machine Learning algorithms on relevant features to predict the different histological types of the mediastinal bulky masses. The aim is to understand how PET radiomic features extracted from bulky masses may predict lymphoma histology and in the future support their histological diagnosis.