Skip to main content

Table 2 The DeLong test of models

From: Development and validation of an ultrasound-based deep learning radiomics nomogram for predicting the malignant risk of ovarian tumours

 

Task 1

Task 2

Training set

Testing set

Training set

Testing set

O-RADS vs Clinic_Sig

P < 0.001

P > 0.05

  

O-RADS vs Rad_Sig

P > 0.05

P < 0.001

  

O-RADS vs DTL_Sig

P < 0.001

P < 0.05

  

O-RADS vs DLR_Nomogram

P < 0.001

P > 0.05

  

Clinic_Sig vs Rad_Sig

P < 0.05

P < 0.001

P > 0.05

P > 0.05

Clinic_Sig vs DTL_Sig

P < 0.001

P > 0.05

P > 0.05

P > 0.05

Clinic_Sig vs DLR_Nomogram

P < 0.05

P > 0.05

P < 0.001

P > 0.05

Rad_Sig vs DTL_Sig

P < 0.001

P < 0.001

P < 0.05

P < 0.05

Rad_Sig vs DLR_Nomogram

P < 0.001

P < 0.001

P < 0.001

P < 0.05

DTL_Sig vs DLR_Nomogram

P < 0.001

P > 0.05

P > 0.05

P > 0.05

  1. Abbreviations: O-RADS ovarian-adnexal reporting and data system, Clinic_Sig clinical signature, Rad_Sig radiomics signature, DTL_Sig deep transfer learning radiomic signature, DLR_Nomogram deep learning radiomic nomogram; vs versus
Back to article page

BioMedical Engineering OnLine

ISSN: 1475-925X

Contact us