发表机构
Microsoft Research; Paul G. Allen School of Computer Science and Engineering, University of Washington; Providence Genomics; Earle A. Chiles Research Institute, Providence Cancer Institute; Providence Research Network（微软研究院; 华盛顿大学保罗·G·艾伦计算机科学与工程学院; 普罗维登斯基因组学公司; 普罗维登斯癌症研究所厄尔·A·奇尔斯研究所; 普罗维登斯研究网络）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对计算病理学中模型局限，提出GigaPath-Flash和GigaTIME-Flash模型用于全切片和肿瘤微环境分析。前者结合特定编码器，计算量少性能优；后者扩展架构预测肿瘤免疫微环境，速度快内存省，共同为相关领域提供开放许可模型及权重。
AI 中文摘要
基础模型已成为计算病理学的驱动力，有潜力通过从大规模组织病理学数据中学习可转移表示来改变癌症诊断、预后和治疗选择。然而，大多数预训练模型仅在图像块级别运行，使用受限许可证且计算成本高，限制了大规模切片级临床和研究应用。本文介绍了GigaPath-Flash和GigaTIME-Flash，用于全切片病理学AI和空间蛋白质组学预测的高效模型。GigaPath-Flash结合了在大规模真实世界组织病理学数据上预训练的22M参数ViT-S块编码器和21M参数LongNet切片编码器，其紧凑块编码器从十亿参数GigaPath（ViT-g）教师模型中提炼而来。GigaPath-Flash以少50倍的计算量保留了GigaPath 97%的平均切片级性能。GigaTIME-Flash扩展此架构以直接从常规H&E图像预测肿瘤免疫微环境，在预测质量上超越了基于CNN的原始GigaTIME，速度快6倍且GPU内存使用少8倍。这些模型与GigaPath和GigaTIME一起形成了一个基于大规模真实世界临床数据预训练的、开放权重且遵循Apache-2.0许可的模型家族。通过发布所有模型和权重，为计算病理学、免疫肿瘤学和精准健康提供了可访问的构建模块。
英文摘要
Foundation models have emerged as a driving force in computational pathology, with the potential to transform cancer diagnosis, prognosis, and treatment selection by learning transferable representations from large-scale histopathology data. A growing landscape of pathology foundation models now spans diverse data sources, architectures, and downstream applications. However, most pretrained models operate only at the image-tile level, use restrictive licenses, and remain computationally expensive, limiting large-scale slide-level clinical and research use. Here, we introduce GigaPath-Flash and GigaTIME-Flash, efficient models for whole-slide pathology AI and spatial proteomics prediction. GigaPath-Flash combines a 22M-parameter ViT-S tile encoder with a 21M-parameter LongNet slide encoder, both pretrained on large-scale real-world histopathology data. Its compact tile encoder is distilled from the billion-parameter GigaPath (ViT-g) teacher and shared by both models. GigaPath-Flash retains 97% of GigaPath's average slide-level performance with 50x less compute. GigaTIME-Flash extends this backbone to predict the tumor immune microenvironment directly from routine H&E images. It surpasses the original CNN-based GigaTIME in prediction quality while running 6x faster and using 8x less GPU memory. Together with GigaPath and GigaTIME, these models form an open-weight, Apache-2.0-licensed family pretrained on large-scale real-world clinical data. By releasing all models and weights, we provide accessible building blocks for computational pathology, immuno-oncology, and precision health.
CommentsModels: https://aka.ms/gigapath-flash (GigaPath-Flash) and https://aka.ms/gigatime-flash (GigaTIME-Flash)
