TITLE: “Multimodal radiomic analysis of biparametric MRI to predict biochemical recurrence after radical prostatectomy.”
ABSTRACT: Integration of information across multiple modalities and biological scales has the potential to improve the prediction of disease outcomes and response to treatments. In this talk, I will discuss our ongoing work to predict prostate cancer aggressiveness by combining information from biparametric MRI. We predict biochemical recurrence (BCR) in 343 men post radical prostatectomy by fusing quantitative image features extracted from T2- and diffusion-weighted scans. We found the fused features improved the prediction of BCR when compared to various baseline models and clinical assessments. In the future, we intend to incorporate genomic data, relating imaging phenotypes to underlying tumor biology.
