Application Values of 2D and 3D Radiomics Models Based on CT Plain Scan in Differentiating Benign from Malignant Ovarian Tumors

Table 3

Predictive performances of a clinical model, radiomics model, and radiomics nomogram model.

Group	Model	Accuracy	95% CI	Sensitivity	Specificity
Training group (2D)	Clinical	0.818	[0.728; 0.889]	0.704	0.956
	Radiomics	0.808	[0.717; 0.880]	0.889	0.711
	Nomogram	0.929	[0.860; 0.971]	0.963	0.889
Validation group (2D)	Clinical	0.829	[0.679; 0.928]	0.727	0.947
	Radiomics	0.805	[0.651; 0.912]	0.818	0.789
	Nomogram	0.902	[0.769; 0.973]	1.000	0.826
Training group (3D)	Clinical	0.808	[0.717; 0.880]	0.704	0.933
	Radiomics	0.798	[0.705; 0.872]	0.907	0.667
	Nomogram	0.929	[0.860; 0.971]	0.963	0.889
Validation group (3D)	Clinical	0.805	[0.651; 0.912]	0.772	0.842
	Radiomics	0.780	[0.624; 0.894]	0.818	0.737
	Nomogram	0.976	[0.871; 0.999]	0.957	1.000