基于主动感知的全切片病理图像智能体视觉推理
Agentic Visual Reasoning in Whole-Slide Pathology Images via Active Perception
浏览论文内容
中文总结 AI 辅助
该研究提出AdaptivePath主动感知框架，通过序列决策实现千兆像素病理切片的视觉推理，在病理VQA基准及TCGA六队列癌症亚型分类上取得最优性能，辅助病理学家诊断。
中文摘要 AI 辅助
全切片视觉推理需要在千兆像素级病理切片中识别稀疏的诊断证据，并整合不同空间尺度的观察结果。现有全切片病理图像（WSI）方法要么将密集采样的图像块压缩为全局表示，要么使用带有启发式区域选择的预训练视觉语言模型，这削弱了预测结果与形态学之间的联系，或缺乏经病理训练的观察策略。我们提出AdaptivePath，一种将WSI证据获取建模为序列决策的主动感知框架。导航器（Navigator）从病理学家审核的标签中学习与问题无关、以异常为导向的导航策略，以选择观察位置和空间范围，避免了成本高昂的特定问题轨迹标注。我们通过交替进行表示学习和近端策略优化来训练该策略，随后用几何和外观一致性目标进行微调，以稳定焦点轨迹。推理过程中，导航器在感兴趣区域（ROI）预算有限的情况下，从低到高倍率分层获取稀疏观察结果。形态学解释器（Morphology Interpreter）将观察结果转换为问题条件化的证据，审议器（Deliberator）评估证据并跨倍率修正中间答案，仲裁者（Arbiter）整合审议历史以生成最终答案。AdaptivePath在WSI和区域病理视觉问答（VQA）基准上实现了零样本的最先进性能，在六个癌症基因组图谱（TCGA）队列的癌症亚型分类中达到80.14%的准确率。在一项盲法诊断效用研究中，使用AdaptivePath选择的观察序列的病理学家达到82.9%的准确率。这些结果表明，学习到的主动感知能够对千兆像素级病理切片进行有效且可追溯的视觉推理。
英文摘要
Whole-slide visual reasoning requires identifying sparse diagnostic evidence in gigapixel pathology slides and integrating observations across spatial scales. Existing WSI methods either compress densely sampled patches into global representations or use pretrained vision-language models with heuristic region selection, weakening links between predictions and morphology or lacking pathology-trained observation policies. We present AdaptivePath, an active-perception framework that formulates WSI evidence acquisition as sequential decision making. The Navigator learns question-agnostic abnormality-driven navigation from pathologist-reviewed labels to select observation locations and spatial extents, avoiding costly question-specific trajectory annotations. We train this policy through alternating representation learning and proximal policy optimization, followed by fine-tuning with geometric and appearance consistency objectives to stabilize focus trajectories. During inference, the Navigator hierarchically acquires sparse observations from low to high magnification under a limited ROI budget. A Morphology Interpreter converts observations into question-conditioned evidence, while the Deliberator evaluates evidence and revises intermediate answers across magnifications. The Arbiter integrates deliberation history to produce final answers. AdaptivePath achieves state-of-the-art zero-shot performance on WSI and region pathology VQA benchmarks and reaches 80.14% accuracy for cancer subtype classification across six TCGA cohorts. In a blinded diagnostic-utility study, pathologists using AdaptivePath-selected observation sequences achieve 82.9% accuracy. These results demonstrate that learned active perception enables effective and traceable visual reasoning over gigapixel pathology slides.
发表机构
- College of Computer Science and Technology, Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）计算机科学与技术学院）
- School of Computing and Data Science, The University of Hong Kong（香港大学计算与数据科学学院）
机构由 AI 辅助整理，请以论文原文为准。
