Deep Learning to Predict EGFR Mutation and PD-L1 Expression Status in Non-Small-Cell Lung Cancer on Computed Tomography Images

<div>Confusion matrix of prediction model in training (a), validation (b), and test cohorts (c), respectively. The micro-average accuracies (ACCs) were 0.90 (95% CI: 0.86–0.93), 0.78 (95% CI: 0.70–0.86), and 0.75 (95% CI: 0.65–0.85) in the training, validation, and test cohorts, respectively.</div>

Journal of Oncology

fig3

Figure 3

Figure 3: Deep Learning to Predict EGFR Mutation and PD-L1 Expression Status in Non-Small-Cell Lung Cancer on Computed Tomography Images 