C3R: Channel Conditioned Cell Representations for unified evaluation in microscopy imaging

ICLR 2026 Conference Submission12844 Authors

Keywords: Representation learning, Microscopy imaging, Multi-channel imaging

TL;DR: C3R builds strong representations for generalization across IHC datasets with unseen channel configurations, outperforming existing methods on both in-distribution and out-of-distribution tasks without retraining.

Abstract: Immunohistochemical (IHC) images reveal detailed information about structures and functions at the subcellular level. However, unlike RGB images, IHC datasets pose challenges for deep learning models due to their inconsistencies in channel count and configuration, stemming from varying staining protocols across laboratories and studies. Although existing approaches build channel-adaptive models, they do not perform zero-shot evaluation across IHC datasets with unseen channel configurations. To address this, we first introduce a structured view of cellular image channels by grouping them into either context or concept, where we treat the context channels as a reference to the concept channels in the image. We leverage this view to propose Channel Conditioned Cell Representations (C3R), a framework that learns representations that transfers well to both in-distribution (ID) and out-of-distribution (OOD) datasets which contain same and different channel configurations, respectively. C3R is a two-fold framework comprising a channel-adaptive encoder architecture and a masked knowledge distillation training strategy, both built around the context-concept principle. We find that C3R outperforms existing benchmarks on both ID and OOD tasks, while yielding state-of-the-art results on CHAMMI-ZS; a zero-shot-style adaptation of the CHAMMI benchmark. Our method opens a new pathway for cross-dataset generalization between IHC datasets, with no need for retraining on unseen channel configurations.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 12844