Figure 4 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group

Abstract

<p>Prediction of RAS pathway mutations using a trained CNN. <b>A,</b> Workflow for deep learning of RAS pathway mutations from FN-RMS WSIs. <b>B</b> and <b>C,</b> Representative (<b>B</b>) H&E images and (<b>C</b>) class activation maps of a RAS pathway wild-type tumor and a tumor with a KRAS p.G12C mutation (VAF = 0.659). <b>D,</b> Confusion matrix for predictions on a test dataset. Micro F1, Macro F1, and Matthew's correlation coefficient shown below. <b>E,</b> Statistics for confusion matrix. <b>F,</b> Average ROC curve from holdout test data.</p>

Ähnliche Arbeiten