Deep Learning for Accurate Diagnosis of Liver Tumor Based on Magnetic Resonance Imaging and Clinical Data.

The sensitivity of Model C and Model D was 91.9% (95% CI 84.7–96.5%) and 90.9% (95% CI 83.4–95.8%), respectively, which were slightly lower than 99.0% (95% CI 94.5–100%) of reader consensus, but did not reach statistical significance ( P = 0.375 and 0.219, respectively, estimated by the McNemar's test using binomial distribution).

also in 111,027 other papers