用动态推理只看关键区域，分析超大病理图快了95%。
Thinking in Scales: Accelerating Gigapixel Pathology Image Analysis via Adaptive Continuous Reasoning
- 按需从低倍到高倍逐步检查，只处理必要区域。
- 比传统方法少用95.95%图像块，推理时间缩短95.62%。
- 适合需要高效分析超大病理切片的研究者。
传统全幻灯片图像（WSI）分析多采用多重实例学习（MIL）范式，对高倍率下的小块图像提取特征并聚合以实现整体判断。然而这种全面的块级处理计算开销巨大，严重限制了WSI分析的效率与可扩展性。为此，我们提出面向病理学的连续思维模型PathCTM，实现针对十亿像素级WSI的高效尺度空间连续推理。PathCTM将诊断推断建模为动态信息搜索过程，自适应地由低倍全局观察过渡至高倍局部检查，并在收集足够证据以有效约束决策不确定性时提前终止推理。具体通过条件计算实现动态尺度切换，结合注意力引导的区域剪枝和置信度感知的早停机制。大量实验表明，相比标准MIL方法，PathCTM将所需图像块数量减少95.95%，推理时间缩短约95.62%，且保持AUC无下降。代码已公开于https://github.com/JSGe-AI/PathCTM。
原文摘要 · Abstract (English)
Traditional whole slide image (WSI) analysis methods typically rely on the multiple instance learning (MIL) paradigm, which extracts patch-level features at high magnification and aggregates them for slide-level prediction. However, such exhaustive patch-level processing is computationally expensive, severely limiting the efficiency and scalability of WSI analysis. To address this challenge, we propose PathCTM (a Pathology-oriented Continuous Thought Model) that enables token-efficient scale-space continuous reasoning for gigapixel WSIs. PathCTM formulates diagnostic inference as a dynamic sequential information pursuit. It progressively transitions from low-magnification global to high-magnification local inspection, and adaptively terminates inference when sufficient evidence is gathered to effectively bound decision uncertainty. Specifically, it uses conditional computation for dynamic scale switching with attention-guided region pruning, coupled with confidence-aware early stopping. Extensive experiments demonstrate that, compared with standard MIL-based methods, PathCTM reduces the number of required image patches by 95.95% and shortens inference time by approximately 95.62%, while maintaining AUC without degradation. Code is available at https://github.com/JSGe-AI/PathCTM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。