Extended Data Fig. 3: Comparison of abnormality-based performance metrics in the internal validation set.
From: Generalist foundation models from a multimodal dataset for 3D computed tomography
This figure provides a detailed analysis of performance metrics, including AUROC, accuracy, precision, and F1 scores, for detecting various abnormalities with our models in the internal validation set, compared to the fully supervised baseline model. The proposed CT-CLIP based models demonstrate improvement over the baseline in almost all comparisons.
