FluoCLIP：荧光显微成像中的染色感知聚焦质量评估
FluoCLIP: Stain-Aware Focus Quality Assessment in Fluorescence Microscopy
把染色语义作为条件注入 CLIP 式视觉语言框架，做染色条件下的序数推理，这个「语义 grounding + 条件化排序」的解耦思路可迁移到其他存在域相关标注偏置的视觉回归任务（如不同成像协议下的质量评分、美学评分）。
原文依据 we introduce FluoMix, the first dataset for stain-aware FQA spanning multiple tissues, fluorescent stains, and focus levels
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论荧光显微成像中的准确聚焦质量评估（FQA）具有挑战性，因为染色相关的光学差异会导致图像间出现异质的聚焦行为。然而，现有方法将聚焦质量视为与染色无关的问题，假设存在一个共享的全局排序。我们为荧光显微成像形式化了染色感知的 FQA，表明由于染色相关的成像特性，聚焦-排序关系在不同染色之间差异显著，从而使上述假设不成立。为支撑这一形式化设定，我们提出了 FluoMix，这是首个面向染色感知 FQA 的数据集，涵盖多种组织、荧光染色和聚焦水平。我们进一步提出 FluoCLIP，一个两阶段的视觉语言框架，它 grounding 染色语义并实现染色条件下的序数推理以进行聚焦预测，从而有效地将染色表征与序数结构解耦。通过显式建模染色相关的聚焦行为，FluoCLIP 持续优于传统 FQA 方法和近期的视觉语言基线，在不同荧光显微成像条件下展现出强泛化能力。代码与数据集已公开于 https://fluoclip.github.io/。
英文原文摘要 1202 字符
Accurate focus quality assessment (FQA) in fluorescence microscopy is challenging due to stain-dependent optical variations that induce heterogeneous focus behavior across images. Existing methods, however, treat focus quality as a stain-agnostic problem, assuming a shared global ordering. We formulate stain-aware FQA for fluorescence microscopy, showing that focus-rank relationships vary substantially across stains due to stain-dependent imaging characteristics and invalidate this assumption. To support this formulation, we introduce FluoMix, the first dataset for stain-aware FQA spanning multiple tissues, fluorescent stains, and focus levels. We further propose FluoCLIP, a two-stage vision-language framework that grounds stain semantics and enables stain-conditioned ordinal reasoning for focus prediction, effectively decoupling stain representation from ordinal structure. By explicitly modeling stain-dependent focus behavior, FluoCLIP consistently outperforms both conventional FQA methods and recent vision-language baselines, demonstrating strong generalization across diverse fluorescence microscopy conditions. Code and dataset are publicly available at https://fluoclip.github.io/.