$${\bf{Micro}}{{\mathbb{S}}}{\bf{plit}}$$: semantic unmixing of fluorescent microscopy data

Abstract Fluorescence microscopy is constrained by optical limits, fluorophore chemistry and finite photon budgets, imposing trade-offs between imaging speed, resolution and phototoxicity. Here we introduce $${\rm{Micro}}{\mathbb{S}}{\rm{plit}}$$ Micro S plit , a deep learning-based computational multiplexing method that enables multiple cellular structures to be imaged simultaneously in a single fluorescent channel and then computationally unmixed. We show that $${\rm{Micro}}{\mathbb{S}}{\rm{plit}}$$ M i c r o S p l i t separates up to four superimposed noisy structures into distinct, denoised image channels, enabling faster and more photon-efficient imaging. Built on Variational Splitting Encoder-Decoder networks, $${\rm{Micro}}{\mathbb{S}}{\rm{plit}}$$ M i c r o S p l i t models a posterior distribution over solutions, allowing uncertainty-aware predictions and the estimation of spatially resolved prediction errors from posterior variability. We demonstrate robust performance across diverse datasets, noise levels and imaging conditions, and show that $${\rm{Micro}}{\mathbb{S}}{\rm{plit}}$$ M i c r o S p l i t improves downstream analysis while reducing photon exposure. All methods, data and trained models are released as open resources, enabling immediate adoption of computational multiplexing in biological imaging.