Multi-kernel graph embedding for detection, Gleason grading of prostate cancer via MRI/MRS

► A method to combine MRI/MRS for distinguishing high versus low-grade CaP regions. ► SeSMiK-GE leverages MKL, semi-supervised learning, and dimensionality reduction. ► MRI/MRS signature outperformed individual protocols, other integration strategies. ► May assist CaP patients for opting active surveillance instead of aggressive therapy.