Fig. 5: Comparison of Diagnostic Performance of Models Trained with Different Data Modalities (Single-modal vs Multi-modal) across All Cohorts.
From: A multicenter clinical AI system study for detection and diagnosis of focal liver lesions
a Comparison of the seven-category classification in the internal validation cohort; b Comparison of the seven-category classification in the external validation cohort of ZZH; c Comparison of the seven-category classification in the external validation cohort of QZH; d Comparison of the seven-category classification in the external validation cohort of NBH; e Comparison of the seven-category classification in the prospective validation cohort of SRRSH; f ROC curves for models using different data modalities in the internal validation cohort. Source data are provided as a Source Data file (Source_data_Figure_5.xlsx).
