PulseAugur
实时 14:36:47

New ARReST strategy slashes WSI storage needs for AI retrieval

研究人员开发了一种名为 ARReST(Antithetical Redundancy Reduction Strategy)的新策略,以解决数字病理学中的存储和检索挑战。该方法通过识别和修剪对跨类判别贡献最小的全切片图像(WSI)中的“对立”块来减少冗余。通过这样做,ARReST 显著压缩了 WSI 索引,降低了存储成本并加快了搜索时间,同时不牺牲检索准确性。在 TCGA 存储库上的实验显示,存储节省了 3% 到 60%,使其适用于可扩展的临床 AI 系统。 AI

影响 使 AI 驱动的临床决策的医学图像索引更具可扩展性和成本效益。

排序理由 该集群包含一篇详细介绍图像索引和检索新方法的 ist 研究论文。

在 arXiv cs.IR (Information Retrieval) 阅读 →

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

New ARReST strategy slashes WSI storage needs for AI retrieval

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Jialiang Geng, Ghazal Alabtah, Saghir Alfasly, Wataru Uegami, H. R. Tizhoosh ·

    Reducing Redundancy in Whole-Slide Image Patching for Scalable Indexing and Retrieval

    arXiv:2606.26157v1 Announce Type: cross Abstract: The rapid growth of digital pathology has created an urgent need for efficient indexing and retrieval of whole slide images (WSIs). This need is intensified by emerging generative AI workflows, particularly retrieval-augmented gen…

  2. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · H. R. Tizhoosh ·

    Reducing Redundancy in Whole-Slide Image Patching for Scalable Indexing and Retrieval

    The rapid growth of digital pathology has created an urgent need for efficient indexing and retrieval of whole slide images (WSIs). This need is intensified by emerging generative AI workflows, particularly retrieval-augmented generation (RAG), which require dependable similarity…