Technology Category
Machine Learning: Calibration & Uncertainty QuantificationComputer Vision: Adversarial Attacks & RobustnessReasoning under Uncertainty: Relational Probabilistic Models
Calibrated Bayesian Deep Learning for Explainable Decision Support Systems Based on Medical Imaging
🤖 AI Summary
This work addresses the issue of miscalibration in deep learning models for medical imaging, where overconfident predictions undermine clinical trustworthiness. The authors propose a general probabilistic calibration framework comprising two components: during training, a Confidence–Uncertainty Boundary loss (CUB-Loss) explicitly constrains high-confidence incorrect predictions and low-confidence correct ones; in post-processing, a Dual Temperature Scaling (DTS) strategy aligns predicted confidence with empirical accuracy. Evaluated on tasks including pneumonia screening, diabetic retinopathy detection, and skin lesion classification, the method significantly improves calibration performance while demonstrating robustness under data scarcity and severe class imbalance, highlighting its strong potential for clinical deployment.
Technology Category
Application Category
📝 Abstract
In critical decision support systems based on medical imaging, the reliability of AI-assisted decision-making is as relevant as predictive accuracy. Although deep learning models have demonstrated significant accuracy, they frequently suffer from miscalibration, manifested as overconfidence in erroneous predictions. To facilitate clinical acceptance, it is imperative that models quantify uncertainty in a manner that correlates with prediction correctness, allowing clinicians to identify unreliable outputs for further review. In order to address this necessity, the present paper proposes a generalizable probabilistic optimization framework grounded in Bayesian deep learning. Specifically, a novel Confidence-Uncertainty Boundary Loss (CUB-Loss) is introduced that imposes penalties on high-certainty errors and low-certainty correct predictions, explicitly enforcing alignment between prediction correctness and uncertainty estimates. Complementing this training-time optimization, a Dual Temperature Scaling (DTS) strategy is devised for post-hoc calibration, further refining the posterior distribution to improve intuitive explainability. The proposed framework is validated on three distinct medical imaging tasks: automatic screening of pneumonia, diabetic retinopathy detection, and identification of skin lesions. Empirical results demonstrate that the proposed approach achieves consistent calibration improvements across diverse modalities, maintains robust performance in data-scarce scenarios, and remains effective on severely imbalanced datasets, underscoring its potential for real clinical deployment.
Problem
Research questions and friction points this paper is trying to address.
calibration
Bayesian deep learning
medical imaging
uncertainty quantification
decision support systems
Innovation
Methods, ideas, or system contributions that make the work stand out.
Bayesian Deep Learning
Uncertainty Calibration
Confidence-Uncertainty Boundary Loss
Dual Temperature Scaling
Explainable AI
🔎 Similar Papers
No similar papers found.
