BioMedical Engineering OnLine

Table 3 Performance of the radiomics–clinical nomogram in discriminating between lung squamous cell carcinoma (LUSC) and lung adenocarcinoma (LUAD) in both training and validation cohorts

From: Elaboration of a multimodal MRI-based radiomics signature for the preoperative prediction of the histological subtype in patients with non-small-cell lung cancer

Cohort	Sen^a	Spe^a	Acc^a	AUC^a	95% CI		p value
Cohort	Sen^a	Spe^a	Acc^a	AUC^a	Lower	Upper	p value
Training	90.0%	76.0%	83.0%	0.901	0.842	0.960	< 0.05
Validation	88.9%	73.3%	79.2%	0.872	0.779	0.965	< 0.05

^aSen, Spe, Acc and AUC indicate the sensitivity, specificity, accuracy and area under the curve of the receiver operating characteristic curve, respectively

Back to article page

ISSN: 1475-925X

Contact us

Submission enquiries: journalsubmissions@springernature.com