Fig. 3From: Deep learning classification of uveal melanoma based on histopathological images and identification of a novel indicator for prognosis of patientsThe deep learning features selection. AÂ The distribution of the lowest mean squared error (MSE) with the corresponding penalization lambda value in LASSO-penalized model. BÂ LASSO coefficient profiles of all deep learning features and the selected criterion of lambda. CÂ Feature weight bar chart for the LASSO-penalized model. DÂ The AUCs distribution of seven machine learning classifiers (SVM, KNN, Decision-Tree, Random-Forest, Extra-Tree, XGBoost, and LightGBM) with tenfold cross-validation. EÂ The accuracy distribution of seven machine learning classifiers in train and test datasets. FÂ The ROC curves of 7 machine learnings in TCGA-UVM cohort. GÂ The ROC curves of 7 machine learnings in HX cohort. HÂ The confusion matrix of SVM classifier in TCGA-UVM cohortBack to article page