AI 中文总结
该研究提出名为“Destroy Me”的混合框架，通过合成六种病理图像人工制品增强数据，训练的nnU-Net模型在肺腺癌分类任务中宏F1和Cohen’s Kappa分别提升10.5%、15%，平衡了鲁棒性与诊断特征保留。
AI 中文摘要
深度学习在病理学中的诊断效用受限于模型对真实世界数据缺陷的脆弱性。当前策略倾向于通过过滤低质量区域获取“完美数据”，这会导致有价值的诊断上下文丢失；我们提出范式转变：设计模型以在不完善环境中表现良好，使用“Destroy Me”（一种用于真实人工制品合成与鲁棒数据增强的混合框架）。我们的方法结合了微调后的Stable Diffusion（通过将人工制品与底层组织结构真实整合以保留形态连续性）与基于物理的程序建模，用于合成六种常见人工制品类型：组织褶皱、沉淀物、模糊、拼接错误、灰尘和笔痕。人工制品保真度使用Kernel Inception Distance（KID）和颜色Wasserstein距离指标评估。在肺腺癌模式分类任务中使用nnU-Net验证该策略，我们确认在“销毁”补丁上训练的模型在独立真实世界数据集上始终优于基线模型。具体而言，我们观察到宏F1分数有10.5%的相对提升，Cohen’s Kappa（κ）系数有15%的相对增加。重要的是，我们的结果表明，选择性的、影响加权的增强对于平衡实际鲁棒性与保留细微诊断特征至关重要。
英文摘要
Deep learning's diagnostic utility in pathology is constrained by model vulnerability to real-world data imperfections. While current strategies favor "perfect data" by filtering low-quality regions, which can lead to the loss of valuable diagnostic context, we propose a paradigm shift: engineering models to thrive in imperfect environments using "Destroy Me", a hybrid framework for realistic artifact synthesis and robust data augmentation. Our approach combines Stable Diffusion, fine-tuned to preserve morphological continuity by realistically integrating artifacts with the underlying tissue architecture, with physics-based procedural modeling to synthesize six common artifact types: tissue folds, precipitates, blur, stitching errors, dust, and pen markers. Artifact fidelity is assessed using Kernel Inception Distance (KID) and color Wasserstein distance metrics. Validating this strategy on lung adenocarcinoma pattern classification with an nnU-Net, we confirm that models trained on "destroyed" patches consistently outperform baselines on independent real-world datasets. Specifically, we observed a 10.5% relative improvement in macro F1-score and a 15% relative increase in the Cohen's Kappa ($κ$) coefficient. Crucially, our results demonstrate that selective, impact-weighted augmentation is vital for balancing practical robustness with the preservation of subtle diagnostic features.
