A Nomogram Combining MRI Multisequence Radiomics and Clinical Factors for Predicting Recurrence of High-Grade Serous Ovarian Carcinoma

Table 2

Performance of the clinical model, radiomics model, and clinical-radiomics model in the training cohort and test cohort.

	Training cohort						Validation cohort
	AUC	ACC	SEN	SPE	PPV	NPV	AUC	ACC	SEN	SPE	PPV	NPV
Clinical model	0.76 (0.68, 0.84)	0.74	0.59	0.89	0.84	0.68	0.67 (0.53, 0.81)	0.59	0.48	0.70	0.61	0.57
DWI radiomics	0.76 (0.68, 0.83)	0.69	0.60	0.77	0.73	0.66	0.74 (0.61, 0.85)	0.65	0.44	0.87	0.77	0.61
T1WI+C radiomics	0.73 (0.64, 0.80)	0.67	0.66	0.68	0.67	0.67	0.72 (0.58, 0.83)	0.70	0.52	0.87	0.80	0.65
FS-T2WI radiomics	0.72 (0.64, 0.80)	0.69	0.83	0.55	0.65	0.76	0.70 (0.56, 0.82)	0.63	0.65	0.61	0.63	0.64
Multiradiomics	0.78 (0.71, 0.86)	0.75	0.64	0.85	0.81	0.70	0.74 (0.61, 0.86)	0.67	0.52	0.83	0.75	0.63
Nomogram	0.83 (0.77, 0.90)	0.78	0.73	0.81	0.77	0.78	0.78 (0.65, 0.90)	0.77	0.80	0.74	0.73	0.81

AUC: area under the curve; ACC: accuracy; SEN: sensitivity; SPE: specificity; PPV: positive predictive value; NPV: negative predictive value; DWI: diffusion-weighted imaging; T1WI + C: contrast-enhanced T1-weighted imaging; FS-T2WI: fat-suppressed T2-wighted imaging.