用空间转录组数据增强病理模型，让其同时理解组织形态与分子状态。
MINT: Molecularly Informed Training with Spatial Transcriptomics Supervision for Pathology Foundation Models
- 引入可学习的转录组标记，分离编码分子信息与形态信息。
- 在577个HEST样本上训练，基因表达预测准确率达0.440（均Pearson r）。
- 适合需要融合多模态病理数据的研究者，尤其关注分子机制的场景。
病理基础模型通过大规模全切片图像自监督预训练学习形态表征，但未显式捕捉组织的分子状态。空间转录组技术通过原位测量基因表达，提供了天然的跨模态监督信号。我们提出MINT（分子感知训练），一种将空间转录组监督融入预训练病理视觉变换器的微调框架。MINT在ViT输入中添加可学习的ST标记，独立编码转录组信息，避免灾难性遗忘；通过DINO自蒸馏和对冻结预训练编码器的显式特征锚定实现稳定优化。在斑点级（Visium）和补丁级（Xenium）分辨率下进行基因表达回归，提供跨空间尺度的互补监督。在577个公开HEST样本上训练后，MINT在HEST-Bench基因表达预测任务上达到均Pearson r = 0.440的最佳表现，在EVA通用病理任务上达到0.803，证明空间转录组监督能有效补充以形态为中心的自监督预训练。
原文摘要 · Abstract (English)
Pathology foundation models learn morphological representations through self-supervised pretraining on large-scale whole-slide images, yet they do not explicitly capture the underlying molecular state of the tissue. Spatial transcriptomics technologies bridge this gap by measuring gene expression in situ, offering a natural cross-modal supervisory signal. We propose MINT (Molecularly Informed Training), a fine-tuning framework that incorporates spatial transcriptomics supervision into pretrained pathology Vision Transformers. MINT appends a learnable ST token to the ViT input to encode transcriptomic information separately from the morphological CLS token, preventing catastrophic forgetting through DINO self-distillation and explicit feature anchoring to the frozen pretrained encoder. Gene expression regression at both spot-level (Visium) and patch-level (Xenium) resolutions provides complementary supervision across spatial scales. Trained on 577 publicly available HEST samples, MINT achieves the best overall performance on both HEST-Bench for gene expression prediction (mean Pearson r = 0.440) and EVA for general pathology tasks (0.803), demonstrating that spatial transcriptomics supervision complements morphology-centric self-supervised pretraining.
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。