LRMIL: 通过高分辨率知识蒸馏实现全切片图像分类的高效低分辨率多实例学习
LRMIL: Efficient Low-Resolution Multiple Instance Learning via High-Resolution Knowledge Distillation for Whole Slide Image Classification
AI总结：
提出LRMIL框架，通过两阶段知识蒸馏将高分辨率知识迁移到低分辨率表示，在推理时仅使用低分辨率图像块，显著降低计算成本并提升分类性能。
摘要：
多实例学习（MIL）已成为数字病理学中全切片图像（WSI）分析的标准范式，因为它无需密集标注即可实现切片级预测。现有的MIL方法通常依赖于高分辨率图像块的详尽提取和编码。然而，这种做法在真实临床环境中存在两个关键限制：难以在较低放大倍数下捕获全局视觉线索，并且由于每张切片包含大量高分辨率图像块而导致巨大的计算开销。为了解决这些限制，我们提出了一种高效的低分辨率多实例学习（LRMIL）框架，该框架将高分辨率知识迁移到低分辨率表示。LRMIL采用两阶段蒸馏策略。首先，图像块级别的跨分辨率蒸馏将低分辨率图像块嵌入与高分辨率表示对齐。其次，切片级知识蒸馏在切片级监督和教师指导下训练低分辨率学生MIL模型。在推理时，LRMIL仅处理低分辨率图像块，大幅减少了数据预处理和计算成本。在多个WSI基准上的大量实验表明，LRMIL在实现更高效推理的同时，始终优于最先进的MIL方法。这些结果凸显了LRMIL作为临床病理学中WSI分析的实用且可扩展的解决方案。
英文摘要：
Multiple instance learning (MIL) has become a standard paradigm for whole slide image (WSI) analysis in digital pathology, as it enables slide-level prediction without dense annotations. Existing MIL methods typically rely on exhaustive extraction and encoding of high-resolution patches. However, this practice suffers from two critical limitations in real-world clinical settings: it struggles to capture global visual cues at lower magnifications, and incurs substantial computational overhead due to the massive number of high-resolution patches per slide. To address these limitations, we propose an efficient low-resolution multiple instance learning (LRMIL) framework that transfers high-resolution knowledge to low-resolution representations. LRMIL adopts a two-stage distillation strategy. First, patch-level cross-resolution distillation aligns low-resolution patch embeddings with high-resolution representations. Second, slide-level knowledge distillation trains a low-resolution student MIL model under both slide-level supervision and teacher guidance. At inference time, LRMIL operates exclusively on low-resolution patches, substantially reducing data preprocessing and computational cost. Extensive experiments on multiple WSI benchmarks demonstrate that LRMIL consistently outperforms state-of-the-art MIL methods while achieving more efficient inference. These results highlight LRMIL as a practical and scalable solution for WSI analysis in clinical pathology.
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。
