用预计算特征+轻量注意力模块，高效做乳腺影像分类
MIL-PF: Multiple Instance Learning on Precomputed Features for Mammography Classification
- 冻结大模型提取特征，只训练4万参数的小聚合模块
- 在临床规模数据上达到当前最优分类效果
- 适合资源有限但需快速迭代的医学图像研究者
现代基础模型提供强大视觉表征，但将其适配高分辨率医学影像仍面临标注稀缺和弱监督挑战。乳腺影像具有图像尺寸大、多视角变化及主要为乳腺级标签的特点，导致端到端微调计算成本高且常不切实际。我们提出基于预计算特征的多实例学习（MIL-PF），结合冻结的基础编码器与轻量级MIL头，实现可扩展的乳腺影像分类。通过预先计算语义表示，并仅训练一个小型任务相关聚合模块（40,000参数），该方法无需重新训练大型骨干网络即可实现高效实验与适应。架构通过基于注意力的聚合显式建模全局组织背景与局部病灶信号。MIL-PF在临床规模数据上实现最先进的分类性能，同时显著降低训练复杂度。代码已开源，确保可复现性。
原文摘要 · Abstract (English)
Modern foundation models provide highly expressive visual representations, yet adapting them to high-resolution medical imaging remains challenging due to limited annotations and weak supervision. Mammography, in particular, is characterized by large images, variable multi-view studies and predominantly breast-level labels, making end-to-end fine-tuning computationally expensive and often impractical. We propose Multiple Instance Learning on Precomputed Features (MIL-PF), a scalable framework that combines frozen foundation encoders with a lightweight MIL head for mammography classification. By precomputing the semantic representations and training only a small task-specific aggregation module (40k parameters), the method enables efficient experimentation and adaptation without retraining large backbones. The architecture explicitly models the global tissue context and the sparse local lesion signals through attention-based aggregation. MIL-PF achieves state-of-the-art classification performance at clinical scale while substantially reducing training complexity. We release the code for full reproducibility.
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。