Table 2 LungCNN-Histo performance.

From: Comparative analysis of machine learning approaches to classify tumor mutation burden in lung adenocarcinoma using histopathology images

Histologic feature

AUC (95% CI)

Combined

TCGA LUAD

DS2

Acinar

0.87 (0.84, 0.90)

0.88 (0.83, 0.92)

0.88 (0.83, 0.92)

Lepidic

0.95 (0.95, 0.99)

0.97 (0.96, 0.99)

0.94 (0.92, 0.96)

Solid

0.96 (0.95, 0.97)

0.97 (0.95, 0.98)

0.95 (0.92, 0.97)

Papillary

0.78 (0.64, 0.85)

0.85 (0.72, 0.91)

0.67 (0.53, 0.96)

Micropapillary

0.97 (0.95, 0.99)

0.99 (0.98, 0.99)

0.96 (0.91, 0.98)

Cribriform

0.93 (0.89, 0.97)

0.92 (0.86, 0.97)

0.94 (0.87, 0.99)

Necrosis

0.98 (0.97, 0.99)

0.98 (0.97, 0.99)

0.99 (0.98, 0.99)

Leukocyte aggregates

0.98 (0.97, 0.99)

0.96 (0.95, 0.98)

0.99 (0.98, 0.99)

Other

0.90 (0.89, 0.92)

0.89 (0.86, 0.91)

0.92 (0.90, 0.94)

  1. The area under the receiver operating characteristic curve (AUC) for the 9 patterns predicted by LungCNN-Histo at the patch-level.
Back to article page