Fig. 4: Receiver operating characteristic (ROC) curves for single-view models and the multi-view ensemble, compared to radiologist performance. | npj Artificial Intelligence

Fig. 4: Receiver operating characteristic (ROC) curves for single-view models and the multi-view ensemble, compared to radiologist performance.

From: SCOPE-MRI: Bankart lesion detection as a case study in data curation and deep learning for challenging diagnoses

Fig. 4

Results are shown on a internal standard MRIs, b MRI arthrograms (MRAs), and c external standard MRIs. The single-view models correspond to those included in the multi-view ensemble. Shaded regions around each curve represent 95% confidence intervals, calculated through bootstrapping with 1000 iterations. Radiologist performance is marked with red X symbols, illustrating sensitivity and false positive rates derived from original radiology reports (internal datasets only). The dashed diagonal line indicates the performance of a random classifier (AUC = 0.50).

Back to article page