发表机构
Sano Centre for Computational Medicine; AGH University of Krakow; Institute of Informatics, HES-SO Valais-Wallis; Faculty of Medicine, University of Geneva (UNIGE)（萨诺计算医学中心; 克拉科夫AGH大学; 瓦莱州瓦利斯高等专业学院信息学研究所; 日内瓦大学医学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出条件层归一化（CLN）结合连续放大训练的单模型，替代多放大倍率模型集成，在PANDA数据集上实现高效尺度不变组织病理学分析，降低成本且性能优异。
AI 中文摘要
数字组织病理学中的全切片图像（WSI）以离散放大倍率采集，编码了从全局组织结构到细粒度细胞形态的互补诊断信息。然而深度学习模型对尺度变化仍很敏感。现有的放大倍率不变方法依赖于预定义离散分辨率的多尺度架构，但在临床部署中，采集放大倍率连续变化，很少与模型的固定训练分辨率对齐，且中间尺度很常见，因此要实现稳健覆盖，否则需要昂贵的特定放大倍率模型集成。我们提出条件层归一化（CLN），这是一种轻量机制，通过小型多层感知机（MLP）从输入像素尺寸生成仿射归一化参数，集成到标准卷积神经网络（CNN）架构中，用于全切片图像分类和分割。在跨一定范围像素尺寸连续采样的图像块上训练后，模型将推理与扫描仪依赖的放大倍率解耦，并在测试时泛化到任意、之前未见过的尺度。在PANDA前列腺癌数据集上，我们的方法平均性能与独立训练的单放大倍率模型相当或更优，且在每个评估的放大倍率（包括训练时未见过的放大倍率）中均排名前三。这将五个模型的集成压缩为单个网络，同时将训练和推理成本降低约4-5倍，而乘加运算次数保持不变。代码可在以下URL获取：this https URL。
英文摘要
Whole slide images (WSIs) in digital histopathology are acquired at discrete magnification levels encoding complementary diagnostic information from global tissue architecture to fine-grained cellular morphology. Yet, deep learning models remain sensitive to scale variation. Existing magnification-invariant methods rely on multi-scale architectures at predefined discrete resolutions, while in clinical deployment the acquisition magnification varies continuously, rarely aligns with a model's fixed training resolution, and intermediate scales are common, so robust coverage otherwise demands a costly ensemble of magnification-specific models. We propose Conditional Layer Normalization (CLN), a lightweight mechanism that generates affine normalization parameters from input pixel size via a small MLP, integrated into standard CNN architectures for both WSI classification and segmentation. Trained on patches sampled continuously across a range of pixel sizes, the model decouples inference from scanner-dependent magnification and generalizes to arbitrary, previously unseen scales at test time. On the PANDA prostate cancer dataset, our approach on average matches or exceeds independently trained single-magnification models and ranks among the top three performers at every evaluated magnification, including those unseen during training. This collapses a five-model ensemble into a single network and reduces training, and inference cost roughly 4-5 times, while leaving the multiply-accumulate count unchanged. The code is available at: https://github.com/aflorkowska/OneModelToMagnifyThemAll.
