DeepCEL0 for 2D Single Molecule Localization in Fluorescence Microscopy
This work addresses the challenge of improving super-resolution imaging in fluorescence microscopy for biological research, representing an incremental advancement in localization algorithms.
The authors tackled the problem of precise molecule localization in high-density fluorescence microscopy frames by proposing DeepCEL0, a deep learning algorithm that incorporates positivity and ℓ0-based constraints via CEL0 relaxation, resulting in faster and more precise localization compared to state-of-the-art methods.
In fluorescence microscopy, Single Molecule Localization Microscopy (SMLM) techniques aim at localizing with high precision high density fluorescent molecules by stochastically activating and imaging small subsets of blinking emitters. Super Resolution (SR) plays an important role in this field since it allows to go beyond the intrinsic light diffraction limit. In this work, we propose a deep learning-based algorithm for precise molecule localization of high density frames acquired by SMLM techniques whose $\ell_{2}$-based loss function is regularized by positivity and $\ell_{0}$-based constraints. The $\ell_{0}$ is relaxed through its Continuous Exact $\ell_{0}$ (CEL0) counterpart. The arising approach, named DeepCEL0, is parameter-free, more flexible, faster and provides more precise molecule localization maps if compared to the other state-of-the-art methods. We validate our approach on both simulated and real fluorescence microscopy data.