Tushar Kataria, Beatrice Knudsen, Shireen Y. Elhabian
TL;DRStainDiffuser 是一种新颖的多任务双扩散架构,用于通过有限的训练预算实现虚拟染色,能同时训练细胞特异性的免疫组织化学染色和基于 HE 的细胞分割。
Abstract
Hematoxylin and Eosin (H&E) staining is the most commonly used for disease
diagnosis and tumor recurrence tracking. Hematoxylin excels at highlighting
nuclei, whereas eosin stains the cytoplasm. However, H&E stain lacks details
for differentiating different types of cells relevant to identifying the grade
of the disease or response to specific treatment vari
本研究提出了一种新的半监督分类模型,命名为 Contrastive Learning with Adaptive Stain Separation and MixUp (CLASSMix),该模型是基于适应性染色分离的苏木精和伊红染色图像的对比学习和混合学习的组合,经在肾细胞癌数据集上的对比分析,证明了该模型在两个数据集上的优越性能。