通过微调提升病理基础模型对扫描仪和染色差异的鲁棒性。
Robustifying pathology foundation models via fine-tuning
- 提出新微调方法，增强病理基础模型对设备与染色变化的适应力。
- 平均提升病理鲁棒性指数23%（0.72→0.87），跨基准性能提高43%。
- 已公开释放两个优化模型，适合临床部署与跨实验室应用。
病理基础模型（FMs）虽能生成强大的切片级表征，但仍易受扫描仪和染色差异影响，制约其在不同实验室的部署。本文提出一种新型微调策略，显著提升病理基础模型对采集因素的鲁棒性。在10种不同模型上应用该方法，均一致提升了鲁棒性与下游性能，未出现性能折损。平均使PathoROB鲁棒性指数提升23%（从0.72升至0.87），在Patho-Bench、HEST与THUNDER联合测试中整体性能提升43%，个别模型鲁棒性最高增72%（Phikon-v2），性能最高增76%（Midnight-12k）。已公开发布Phikon-v2（Phaet）与Midnight-12k（Mascaret）的微调版本，链接见https://huggingface.co/wearewaiv/models。
原文摘要 · Abstract (English)
Pathology foundation models (FMs) produce powerful tile-level representations which remain sensitive to scanner and staining variability, undermining deployment across laboratories. We develop a novel fine-tuning recipe that improves the robustness of pathology FMs to acquisition factors. Applied to ten different FMs, our fine-tuning strategy consistently improves robustness for every model as well as downstream performance, with no observed trade-off. On average, it raises the PathoROB robustness index by 23% (from 0.72 to 0.87) and increases the overall cross-benchmark performance by 43% on Patho-Bench, HEST and THUNDER combined, with individual gains reaching up to 72% in robustness (Phikon-v2) and 76% in performance (Midnight-12k). We publicly release the fine-tuned versions of Phikon-v2 (Phaet) and Midnight-12k (Mascaret) at https://huggingface.co/wearewaiv/models.
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。