Figure 2 | Scientific Reports

Figure 2

From: Predicting tumor recurrence on baseline MR imaging in patients with early-stage hepatocellular carcinoma using deep machine learning

Figure 2

Kaplan–Meier analysis of RFS for each of the analyzed time frames according to algorithm predictions. The red curves represent patients the algorithm classifies as “recurrent” (High-risk), while the green curves represent patients the algorithm classifies as “non-recurrent” (Low-risk). Each event on the green curve represents prediction inaccuracy (false-negative) while each event on the red curve represents an accurate prediction of recurrence (positive predictive value).

Back to article page