A cognitive computing tool for differential diagnosis between metastases and high grade gliomas

This paper describes the research carried out in the 3 years of the PhD in Information and Communication Technology for Health (ICTH) on the topic of Cognitive Computing Systems for Neuroncology at the Department of Electrical Engineering and Information Technologies (DIETI) of the University of Naples "Federico II". The aim of the work is to design an innovative computational system based on cognitive computing technologies for the analysis of data derived from magnetic resonance images (MRI) in patients with brain tumors of unknown origin. To do this, the open source deep learning framework based on PyTorch for medical data called FuseMedML was used, the main objective is to obtain a supervised binary classification model that allows the timely identification of the two most common malignant brain tumors of adulthood, which require different therapeutic strategies and clinical-radiological monitoring.