ImmuVis: Hyperconvolutional Foundation Model for Imaging Mass Cytometry
This addresses a key bottleneck in imaging mass cytometry for biomedical researchers by enabling efficient and flexible analysis of diverse tissue profiling data.
The paper tackles the problem of modeling multiplex imaging data with varying marker sets by introducing ImmuVis, a hyperconvolutional foundation model that adapts to arbitrary marker subsets without retraining, achieving state-of-the-art performance in tasks like virtual staining and classification with lower compute cost than transformer alternatives.
We present ImmuVis, an efficient convolutional foundation model for imaging mass cytometry (IMC), a high-throughput multiplex imaging technology that handles molecular marker measurements as image channels and enables large-scale spatial tissue profiling. Unlike natural images, multiplex imaging lacks a fixed channel space, as real-world marker sets vary across studies, violating a core assumption of standard vision backbones. To address this, ImmuVis introduces marker-adaptive hyperconvolutions that generate convolutional kernels from learned marker embeddings, enabling a single model to operate on arbitrary measured marker subsets without retraining. We pretrain ImmuVis on the largest to-date dataset, IMC17M (28 cohorts, 24,405 images, 265 markers, over 17M patches), using self-supervised masked reconstruction. ImmuVis outperforms SOTA baselines and ablations in virtual staining and downstream classification tasks at substantially lower compute cost than transformer-based alternatives, and is the sole model that provides calibrated uncertainty via a heteroscedastic likelihood objective. These results position ImmuVis as a practical, efficient foundation model for real-world IMC modeling.