Conformal coronary calcification volume estimation with conditional coverage via histogram clustering
This work addresses the need for reliable automated reporting in medical imaging to prevent unnecessary patient burden and system costs, representing an incremental improvement in calibration techniques.
The paper tackled the problem of over-reporting coronary calcium scores in CT scans by proposing a cluster-based conditional conformal prediction framework to provide calibrated score intervals from segmentation networks, achieving similar coverage with improved triage metrics compared to conventional methods.
Incidental detection and quantification of coronary calcium in CT scans could lead to the early introduction of lifesaving clinical interventions. However, over-reporting could negatively affect patient wellbeing and unnecessarily burden the medical system. Therefore, careful considerations should be taken when automatically reporting coronary calcium scores. A cluster-based conditional conformal prediction framework is proposed to provide score intervals with calibrated coverage from trained segmentation networks without retraining. The proposed method was tuned and used to calibrate predictive intervals for 3D UNet models (deterministic, MCDropout and deep ensemble) reaching similar coverage with better triage metrics compared to conventional conformal prediction. Meaningful predictive intervals of calcium scores could help triage patients according to the confidence of their risk category prediction.