Fig. 4: Evaluation results for ESV1 on compression sequence level.
From: Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning
Receiver operator characteristics for the correct compression classification per ultrasound sequence/anatomical landmark on EVS1 (a). Confusion matrices (b) at optimal thresholds (* in (a)) per fold. Frame colours correspond to ROC fold colours in (a). Vessel status is extracted automatically through the ML models from the 121 available anatomical landmark sequences in EVS1.
