English(EN) Multi-Rater Calibrated Segmentation Models

新方法使用序数学习改进医学分割模型校准

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-04 10:35

研究人员开发了一种新方法，用于改进医学图像分割模型的校准，特别是在多个专家标注显示出显著分歧时。该方法将多评分者监督重新构建为序数学习问题，将体素级别的评分者一致性视为有序目标。这使得模型置信度能够更好地反映训练数据中的经验变异性，从而在不牺牲分割准确性的情况下提高校准效果。 AI

影响通过提高分割任务中置信度的估计，增强了临床环境中AI模型的可靠性。

排序理由该集群包含一篇详细介绍AI模型校准新方法的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Meritxell Riera-Mar\'in, Javier Garc\'ia L\'opez, J\'ulia Rodr\'iguez-Comas, Miguel A. Gonz\'alez Ballester, Adrian Galdran · 2026-05-05 04:00

多评分者校准分割模型

arXiv:2605.02437v1 Announce Type: new Abstract: Objective: Accurate probability estimates are essential for the safe deployment of medical image segmentation models in clinical decision-making. However, modern deep segmentation networks are often poorly calibrated, a problem exac…
arXiv cs.CV TIER_1 English(EN) · Adrian Galdran · 2026-05-04 10:35

多评估者校准分割模型

Objective: Accurate probability estimates are essential for the safe deployment of medical image segmentation models in clinical decision-making. However, modern deep segmentation networks are often poorly calibrated, a problem exacerbated when multiple expert annotations exhibit…