Prostate cancer is one of the most prevalent cancers in the male population. Its diagnosis and classification rely on unspecific measures such as PSA levels and DRE, followed by a biopsy, where an aggressiveness level is assigned in the form of Gleason Score. Efforts have been made in the past to use radiomics coupled with machine learning to predict prostate cancer aggressiveness from clinical images, showing promising results.
Thus, the main goal of this work “Prediction of Prostate Cancer Disease Aggressiveness Using Bi-Parametric Mri Radiomics” was to develop supervised machine learning models exploiting radiomic features extracted from bpMRI examinations, to predict biological aggressiveness; 288 classifiers were developed, corresponding to different combinations of pipeline aspects, namely, type of input data, sampling strategy, feature selection method, and machine learning algorithm.
The work is co-authored by Francisco Couto, LASIGE’s integrated member, and Ana Rodrigues (Champalimaud Foundation, Faculty of Sciences), João Santinha (Champalimaud Foundation, Instituto Superior Técnico), Bernardo Galvão (Faculty of Sciences and Technology), Celso Matos (Champalimaud Foundation), and Nickolas Papanikolaou (Champalimaud Foundation).
It is available here.