unsupervised learning

A robust collaborative clustering method has been developed in a Bayesian framework to simultaneously cluster patients and imaging features into distinct groups respectively, aiming to learn a compact set of discriminative features in radiomics studies. Experiments on synthetic data have demonstrated the effectiveness of the proposed approach in data clustering, and evaluation results on an FDG-PET/CT dataset of rectal cancer patients have demonstrated that the proposed method outperforms alternative methods in terms of both patient stratification and prediction of patient clinical outcomes. read more