Table 3 AUROC, BA, F1 Score and MCC for the best modelling algorithms trained on both radiomics segmentation modes (GTV and CTV).

From: The importance of planning CT-based imaging features for machine learning-based prediction of pain response

Segmentation

Model

AUROC

BA

F1

MCC

GTV

SVM

0.58 ± 0.01

0.54 ± 0.02

0.33 ± 0.03

0.08 ± 0.04

CTV

RFC

0.62 ± 0.01

0.58 ± 0.02

0.37 ± 0.03

0.15 ± 0.04

Back to article page