病理图像需专用模型，不能照搬自然图像大模型
Beyond the Failures: Rethinking Foundation Models in Pathology
- 提出病理图像应设计专用模型，而非套用自然图像大模型
- 现有方法在组织学图像上准确率低、计算开销大、结果不稳定
- 适合医学影像研究者与临床AI开发者参考
尽管在视觉和语言领域取得成功，基础模型在病理学领域表现不佳，表现为准确率低、结果不稳定且计算开销巨大。这些缺陷并非调参问题，而是深层概念错配所致：密集嵌入无法捕捉组织的组合丰富性，现有架构继承了自监督学习、图像块设计及对噪声敏感预训练中的固有缺陷。生物复杂性与领域创新不足进一步拉大差距。证据表明，病理学需要为生物图像专门设计的模型，而非沿用大规模自然图像方法——其假设不适用于组织学图像。
原文摘要 · Abstract (English)
Despite their successes in vision and language, foundation models have stumbled in pathology, revealing low accuracy, instability, and heavy computational demands. These shortcomings stem not from tuning problems but from deeper conceptual mismatches: dense embeddings cannot represent the combinatorial richness of tissue, and current architectures inherit flaws in self-supervision, patch design, and noise-fragile pretraining. Biological complexity and limited domain innovation further widen the gap. The evidence is clear-pathology requires models explicitly designed for biological images rather than adaptations of large-scale natural-image methods whose assumptions do not hold for tissue.
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。