# Confidence-Uncertainty Boundary Calibration for Bayesian Deep Learning in Medical Image Analysis

Source: [Confidence-Uncertainty Boundary Calibration for Bayesian Deep Learning in Medical Image Analysis](<https://www.sota2.com/research/paper/698eb046c97a0b3e3b5e6873>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-24T05:00:22.884Z

Authors: Hua Xu, Juli\\'an D. Arias-Londo\\~no, Juan I. Godino-Llorente

Published: 2026-02-12T14:03:41.000Z

## 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. To address this necessity, this paper proposes a probabilistic optimization framework grounded in Bayesian deep learning. Specifically, the Confidence-Uncertainty Boundary Curve (CUBC) is first explored as an intermediate operational target. Grounded in this target, a novel Confidence-Uncertainty Boundary Loss (CUB-Loss) is proposed to regularize the alignment between prediction confidence and uncertainty estimates during training, imposing penalties on high-certainty errors and low-certainty correct predictions. Upon completion of training optimization, a Boundary Curve Calibration Error (BCCE) metric is further introduced to measure the degree of boundary alignment in the calibrated model. Building on this measurement, a Dual Temperature Scaling (DTS) strategy is devised to perform post-hoc refinement, further adjusting the posterior predictive distribution across different confidence-uncertainty regions. 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 improves uncertainty calibration across diverse modalities, maintains robust performance in data-scarce scenarios, and remains effective on severely imbalanced datasets, underscoring its potential for real clinical deployment.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Out-of-Distribution Detection on APTOS Near-OOD 2019 (test)](<https://www.sota2.com/research/sota/out-of-distribution-detection-on-aptos-near-ood-2019-test.md>): Out-of-Distribution Detection; APTOS Near-OOD 2019 (test); AUROC: 74.2.

- [Identification of skin lesions on HAM10000](<https://www.sota2.com/research/sota/identification-of-skin-lesions-on-ham10000.md>): Identification of skin lesions; HAM10000; Accuracy (%): 85.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.11973>)

[PDF](<https://arxiv.org/pdf/2602.11973.pdf>)
