🤖 AI Summary
To address the challenge of multi-class cell counting in immunohistochemistry (IHC) images—complicated by staining overlap, biomarker expression heterogeneity, and morphological diversity—we propose a knowledge distillation framework integrating multiple foundation models. Our method introduces a rank-aware teacher selection mechanism that dynamically evaluates and aggregates teacher capabilities via global-local patch ranking; and a vision-language alignment fine-tuning strategy that leverages structured text prompts to generate semantic anchors, jointly encoding class identity and density information. Built upon regression-based density map estimation, the framework enables end-to-end prediction of multi-class cell densities. Evaluated across 12 IHC biomarkers and 5 tissue types, it significantly outperforms state-of-the-art methods, achieving exceptional agreement with pathologist counts (ICC > 0.95). Moreover, it demonstrates strong generalizability on H&E-stained images.
📝 Abstract
Accurate cell counting in immunohistochemistry (IHC) images is critical for quantifying protein expression and aiding cancer diagnosis. However, the task remains challenging due to the chromogen overlap, variable biomarker staining, and diverse cellular morphologies. Regression-based counting methods offer advantages over detection-based ones in handling overlapped cells, yet rarely support end-to-end multi-class counting. Moreover, the potential of foundation models remains largely underexplored in this paradigm. To address these limitations, we propose a rank-aware agglomeration framework that selectively distills knowledge from multiple strong foundation models, leveraging their complementary representations to handle IHC heterogeneity and obtain a compact yet effective student model, CountIHC. Unlike prior task-agnostic agglomeration strategies that either treat all teachers equally or rely on feature similarity, we design a Rank-Aware Teacher Selecting (RATS) strategy that models global-to-local patch rankings to assess each teacher's inherent counting capacity and enable sample-wise teacher selection. For multi-class cell counting, we introduce a fine-tuning stage that reformulates the task as vision-language alignment. Discrete semantic anchors derived from structured text prompts encode both category and quantity information, guiding the regression of class-specific density maps and improving counting for overlapping cells. Extensive experiments demonstrate that CountIHC surpasses state-of-the-art methods across 12 IHC biomarkers and 5 tissue types, while exhibiting high agreement with pathologists' assessments. Its effectiveness on H&E-stained data further confirms the scalability of the proposed method.