Meeting Banner
Abstract #4034

Ensemble learning-based analysis of T1-weighted and T2-weighted magnetic resonance (MR) radiomics for the prediction of prostate cancer grades with small-scale cohort

Huipeng Ren1 and Zhuanqin Ren1

1Baoji Central Hospital, Baoji, China

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´╝îand 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.

Join Here