PulseAugur
实时 10:07:40

MARVEL框架提升临床AI诊断的OOD检测能力

研究人员开发了MARVEL,一种用于改进临床AI诊断系统中分布外(OOD)检测的新方法。MARVEL通过在不平衡的医学数据集上进行训练,并在临床相关的OOD谱系上进行评估,来解决当前方法的局限性。该框架包括一个用于非线性边界的非线性von Mises-Fisher分类器、一个用于处理数据不平衡的多专家系统,以及一个用于区分内点和外点的异常值专家。在RFMiD、ISIC2019和NCTCRC数据集上的评估显示,与最先进的方法相比,误报率显著降低。 AI

影响 通过改进对未知病例的识别能力,提高了AI诊断的可靠性,从而实现了更安全的AI辅助医疗工作流程。

排序理由 该项目是一篇研究论文,详细介绍了一种新的分布外检测方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

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

MARVEL框架提升临床AI诊断的OOD检测能力

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · A. S. Anudeep, Vaanathi Sundaresan ·

    MARVEL: Margin-Aware Robust von Mises-Fischer Expert Learning for Long-Tailed Out-of-Distribution Detection

    arXiv:2607.02435v1 Announce Type: new Abstract: For clinical deployment, it is essential that automated diagnostic systems remain reliable when confronted with previously unseen cases, yet deep models routinely misclassify out-of-distribution (OOD) inputs with high confidence, un…

  2. arXiv cs.CV TIER_1 English(EN) · Vaanathi Sundaresan ·

    MARVEL: Margin-Aware Robust von Mises-Fischer Expert Learning for Long-Tailed Out-of-Distribution Detection

    For clinical deployment, it is essential that automated diagnostic systems remain reliable when confronted with previously unseen cases, yet deep models routinely misclassify out-of-distribution (OOD) inputs with high confidence, underscoring the need for more robust OOD detectio…