病理基础模型的单 GPU 任务适配用于全切片图像分析
Single GPU Task Adaptation of Pathology Foundation Models for Whole Slide Image Analysis
AI总结:
本文提出单 GPU 病理基础模型任务适配方法 TAPFM,利用 ViT 注意力进行 MIL 聚合并分离计算图以稳定训练,在膀胱癌和肺腺癌突变预测上优于传统方法,使 PFM 适配在标准硬件上实用化。
摘要:
病理基础模型(PFMs)已成为分析全切片图像(WSIs)的强大工具。然而,将这些预训练的 PFMs 适配到特定临床任务面临相当大的挑战,主要原因是对于十亿像素级图像仅有弱(WSI 级)标签可用,这需要采用多实例学习(MIL)范式来进行有效的 WSI 分析。本文提出了一种新颖的单 GPU 病理基础模型任务适配方法(TAPFM),该方法使用视觉 Transformer(ViT)注意力进行 MIL 聚合,同时优化特征表示和注意力权重。所提出的方法为 MIL 聚合器和 PFM 保持独立的计算图,以在端到端适配过程中建立稳定的训练动态,使其与下游任务目标保持一致。在膀胱癌和肺腺癌的突变预测任务上,跨机构队列和 TCGA 队列进行评估,TAPFM 一致优于传统方法,其中 H-Optimus-0(TAPFM)优于各基准方法。TAPFM 也能有效处理可操作突变的多标签分类。因此,TAPFM 使得强大的预训练 PFMs 在标准硬件上适配各种临床应用变得切实可行。
英文摘要:
Pathology foundation models (PFMs) have emerged as powerful tools for analyzing whole slide images (WSIs). However, adapting these pretrained PFMs for specific clinical tasks presents considerable challenges, primarily due to the availability of only weak (WSI-level) labels for gigapixel images, necessitating multiple instance learning (MIL) paradigm for effective WSI analysis. This paper proposes a novel approach for single-GPU \textbf{T}ask \textbf{A}daptation of \textbf{PFM}s (TAPFM) that uses vision transformer (\vit) attention for MIL aggregation while optimizing both for feature representations and attention weights. The proposed approach maintains separate computational graphs for MIL aggregator and the PFM to create stable training dynamics that align with downstream task objectives during end-to-end adaptation. Evaluated on mutation prediction tasks for bladder cancer and lung adenocarcinoma across institutional and TCGA cohorts, TAPFM consistently outperforms conventional approaches, with H-Optimus-0 (TAPFM) outperforming the benchmarks. TAPFM effectively handles multi-label classification of actionable mutations as well. Thus, TAPFM makes adaptation of powerful pre-trained PFMs practical on standard hardware for various clinical applications.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。