Skip to main content

Table 2 Consistency between the results of nine pathologists’ interpretation of Ki-67LI using VA, MC, SRC and AI and the gold standard

From: Artificial intelligence-assisted interpretation of Ki-67 expression and repeatability in breast cancer

Pathologist

ICC(95%CI)

P

VA

MC

SRC

AI

A

0.735 (0.652,0.801)

0.764 (0.688,0.823)

0.884 (0.843,0.914)

0.975 (0.965,0.982)

<0.001

B

0.746 (0.665,0.809)

0.753 (0.674,0.815)

0.888 (0.848,0.917)

0.961 (0.946,0.971)

<0.001

C

0.751 (0.672,0.813)

0.764 (0.688,0.823)

0.885 (0.844,0.915)

0.956 (0.940,0.968)

<0.001

D

0.829 (0.772,0.874)

0.883 (0.842,0.914)

0.977 (0.969,0.984)

0.976 (0.966,0.982)

<0.001

E

0.746 (0.688,0.823)

0.860 (0.811,0.896)

0.981 (0.973,0.986)

0.985 (0.979,0.989)

<0.001

F

0.764 (0.689,0.824)

0.878 (0.836,0.910)

0.971 (0.961,0.979)

0.985 (0.979,0.989)

<0.001

G

0.975 (0.965,0.982)

0.983 (0.977,0.988)

0.987 (0.982,0.990)

0.988 (0.983,0.991)

<0.001

H

0.981 (0.974,0.986)

0.982 (0.976,0.987)

0.983 (0.977,0.988)

0.990 (0.986,0.993)

<0.001

I

0.980 (0.973,0.986)

0.982 (0.975,0.987)

0.987 (0.982,0.990)

0.988 (0.983,0.991)

<0.001

X

  

0.989 (0.985,0.992)

0.994 (0.992,0.996)

<0.001

Y

  

0.992 (0.990,0.995)

0.995 (0.993,0.996)

<0.001

Z

  

0.994 (0.992,0.996)

0.995 (0.993,0.996)

<0.001

  1. P < 0.05 is statistically significant
  2. VA microscopic visual assessment, MC microscopic manual counting, SRC standard comparison card, AI artificial intelligence, LI Label Index