How a machine improves PI-RADS classification in prostatic cancer

This is a practical example of how a machine can learn reading prostatic MR, extracting radiomics and improving the PI-RADS classifciation.




Key points:

  • Machine-based analysis of MR radiomics outperformed in TZ cancer against PI-RADS
  • Adding MR radiomics significantly improved the performance of PI-RADS
  • DKI-derived Dapp and Kapp were two strong markers for the diagnosis of PCa

Article: Machine learning-based analysis of MR radiomics can help to improve the diagnostic performance of PI-RADS v2 in clinically relevant prostate cancer

Authors: Jing Wang, Chen-Jiang Wu, Mei-Ling Bao, Jing Zhang, Xiao-Ning Wang and Yu-Dong Zhang