PulseAugur
实时 13:18:05
English(EN) Confidence is Not Reliability: Rethinking MC Dropout in Brain Tumour Segmentation

MC Dropout在脑肿瘤分割中的可靠性受到质疑

研究人员调查了蒙特卡洛Dropout(MC Dropout)在MRI扫描中分割脑肿瘤的可靠性,发现虽然它可以将不确定性与错误对齐,但可能并不总是保证临床安全。在一项针对126名BraTS21患者的研究中,MC Dropout表现出强大的不确定性-错误对齐能力,正确地将错误体素排名更高,并识别出分割性能显著较低的亚组。然而,该研究还揭示,全局对齐指标可能会掩盖关键区域特定的校准失败,例如其中一个模型尽管整体AUROC得分很高,但在临床上至关重要的子区域上表现出严重的校准失误。研究结果强调,在选择用于临床部署的模型时,除了标准指标外,还需要进行子区域特定的校准评估。 AI

影响 强调了医疗AI中更鲁棒的不确定性量化需求,以确保患者安全和可靠的临床部署。

排序理由 该集群包含一篇详细介绍AI模型可靠性新研究的论文。

在 arXiv cs.LG 阅读 →

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]

  1. arXiv cs.LG TIER_1 English(EN) · Xin Ci Wong, Duygu Sarikaya, Kieran Zucker, Marc De Kamps, Nishant Ravikumar ·

    Confidence is Not Reliability: Rethinking MC Dropout in Brain Tumour Segmentation

    arXiv:2606.19300v1 Announce Type: cross Abstract: Glioma segmentation in multiparametric MRI is a critical component of treatment planning. A segmentation model that fails silently on treatment-critical sub-regions represents a patient safety risk that overlap-based metrics such …

  2. arXiv cs.CV TIER_1 English(EN) · Nishant Ravikumar ·

    Confidence is Not Reliability: Rethinking MC Dropout in Brain Tumour Segmentation

    Glioma segmentation in multiparametric MRI is a critical component of treatment planning. A segmentation model that fails silently on treatment-critical sub-regions represents a patient safety risk that overlap-based metrics such as Dice scores cannot expose. We ask whether voxel…