Table 1 The amount of true positives (TP), true negatives (TN), false positives (FP) and false negatives (FN) with median and interquartile range (IQR) of the CNN on 100 runs of the data in addition to the results with the clinical interpretation with the hold-out (test) dataset.

From: Classification of ischemia from myocardial polar maps in 15O–H2O cardiac perfusion imaging using a convolutional neural network

Method

TP

TP IQR

TN

TN IQR

FP

FP IQR

FN

FN IQR

CNN

13

2

25

0

1

0

7

2

Clinical

15

N/A

25

N/A

1

N/A

5

N/A