Machine learning-based radiomics model to predict benign and malignant PI-RADS v2.1 category 3 lesions: a retrospective multi-center study

Table 3 The performance of each model for predicting any tumors in PI-RADS 3 lesions

Modality	Training set				Internal test set				External validation set				Mean AUC*	P value
Modality	AUC	ACC	SEN	SPE	AUC	ACC	SEN	SPE	AUC	ACC	SEN	SPE	Mean AUC*	P value
T2WI-model	0.811	0.784	0.614	0.867	0.678	0.643	0.842	0.545	0.589	0.650	0.500	0.722	0.634	0.547
DWI-model	0.717	0.735	0.557	0.822	0.712	0.730	0.684	0.753	0.598	0.638	0.616	0.648	0.655	0.437
ADC-model	0.840	0.780	0.773	0.783	0.650	0.565	0.921	0.390	0.640	0.613	0.654	0.593	0.645	0.848
Integrated-model	0.855	0.746	0.920	0.661	0.801	0.748	0.763	0.740	0.754	0.763	0.846	0.722	0.778	0.047
PSAD-model	0.660	0.623	0.761	0.556	0.637	0.583	0.763	0.494	0.623	0.575	0.846	0.444	0.630	0.036

T2WI T2 weighted imaging; DWI diffusion weighted imaging; ADC apparent diffusion coefficient; PSAD PSA-density; AUC area under the receiver operating characteristic curve; ACC accuracy; SEN sensitivity; SPE specificity
^*Mean AUC = [AUC(Internal test set) + AUC(External validation set)]/2
The P values from the non-inferiority tests

ISSN: 1471-2342