Information-Distilled Generative Label-Free Morphological Profiling Encodes Cellular Heterogeneity

Abstract

Image-based cytometry faces constant challenges due to technical variations arising from different experimental batches and conditions, such as differences in instrument configurations or image acquisition protocols, impeding genuine biological interpretation of cell morphology. Existing solutions, often necessitating extensive pre-existing data knowledge or control samples across batches, have proved limited, especially with complex cell image data. To overcome this, we introduce Cyto-Morphology Adversarial Distillation (CytoMAD), a self-supervised multi-task learning strategy that distills biologically relevant cellular morphological information from batch variations, enabling integrated analysis across multiple data batches without complex data assumptions or extensive manual annotation. Unique to CytoMAD is its "morphology distillation", symbiotically paired with deep-learning image-contrast translation - offering additional interpretable insights into the label-free morphological profiles. We demonstrate the versatile efficacy of CytoMAD in augmenting the power of biophysical imaging cytometry. It allows integrated label-free classification of different human lung cancer cell types and accurately recapitulates their progressive drug responses, even when trained without the drug concentration information. We also applied CytoMAD to jointly analyze tumor biopsies across different non-small-cell lung cancer patients and reveal previously unexplored biophysical cellular heterogeneity, linked to epithelial-mesenchymal plasticity, that standard fluorescence markers overlook. CytoMAD holds promises to substantiate the wide adoption of biophysical cytometry for cost-effective diagnostic and screening applications.