Insights into Imaging

Table 2 Performance of the radiomics model, deep learning model, and transcriptomics model in the training and testing cohorts

From: A multi-model based on radiogenomics and deep learning techniques associated with histological grade and survival in clear cell renal cell carcinoma

Different models	Training cohort (n = 142)				Testing cohort (n = 35)
Different models	AUC (95%CI)	SEN	SPE	ACC	AUC (95%CI)	SEN	SPE	ACC
Radiomics model	0.858 (0.787–0.929)	0.964	0.569	0.803	0.820 (0.674–0.966)	0.752	0.500	0.771
Deep learning model	0.851 (0.783–0.919)	0.726	0.897	0.796	0.840 (0.694–0.986)	0.762	0.929	0.829
Transcriptomics model	0.871 (0.813–0.929)	0.750	0.862	0.800	0.816 (0.674–0.959)	0.667	0.929	0.771
Combined model	0.946 (0.912–0.980)	0.952	0.862	0.916	0.864 (0.734–0.994)	0.857	0.643	0.771

Abbreviations: AUC area under the curve, SEN sensitivity, SPE specificity, ACC accuracy, 95% CI 95% confidence interval

Back to article page