Traditionally, PCA diagnosis and classification are based on prostate specific antigen (PSA) levels, ultrasound and biopsy. This study combines Adasyn and XGBOOST methods to compare the predictive effects of T1-weighted, T2-weighted and T1-T2 co-registration MR images on prostate cancer. The results showed that the integrated learning algorithm using XGBoost can effectively predict prostate cancer grade based on T2WI radiomics features，and T2WI has a better prognostic performance compared with T1-T2 fusion images.
This abstract and the presentation materials are available to members only; a login is required.