Junyu Guo1, Lauren Hinojosa1, Yin Xi1, Keith Husley1, and Ivan Pedrosa1
1Radiology, UT southwestern medical center, Dallas, TX, United States
1Radiology, UT southwestern medical center, Dallas, TX, United States
Radiomics and deep learning technique have the potential to facilitate the prediction of clear cell renal carcinoma cancer (ccRCC) subjects even using T2w images only. These results were compared against previously reported performance of the clear cell likelihood score (ccLS) criteria.
Figure 1. Receiver operating curves (ROC) for three models using radiomics and results of deep learning and human prediction. DL1: deep learning model using a single T2w slice; DL2: deep learning model using a T2w slice and its tumor and kidney masks. ccLS 4/5 and ccLS 3/4/5: clear cell likelihood score 4 and 5, or 3, 4 and 5 from human readers based on multiparametric MRI.
Table 2
