Conformal Risk Control for Semantic Uncertainty Quantification in Computed Tomography
This work addresses the need for clinically meaningful uncertainty quantification in medical imaging to improve patient care and build trust among developers, physicians, and regulatory agencies, representing an incremental advancement in domain-specific methods.
The authors tackled the problem of uncertainty quantification in medical imaging by introducing a conformal risk control procedure that ensures high-probability coverage of ground-truth images in computed tomography, resulting in tighter uncertainty intervals with valid coverage on real-world CT data.
Uncertainty quantification is necessary for developers, physicians, and regulatory agencies to build trust in machine learning predictors and improve patient care. Beyond measuring uncertainty, it is crucial to express it in clinically meaningful terms that provide actionable insights. This work introduces a conformal risk control (CRC) procedure for organ-dependent uncertainty estimation, ensuring high-probability coverage of the ground-truth image. We first present a high-dimensional CRC procedure that leverages recent ideas of length minimization. We make this procedure semantically adaptive to each patient's anatomy and positioning of organs. Our method, sem-CRC, provides tighter uncertainty intervals with valid coverage on real-world computed tomography (CT) data while communicating uncertainty with clinically relevant features.