Table 4 Predictive performance results for intratumoral region for CR and DLB models. Values shown are from the random seed with highest training set accuracy. The DLB model performed similarly to CR in the validation set. In the testing set, DLB model outperformed CR model in numerous metrics, including NPV, accuracy, and YI. This indicates the DLB model might be more generalizable and less sensitive to pixel size differences

From: Preoperative prediction of lymph node metastasis using deep learning-based features