The nanoscale resolution of super-resolution microscopy has now enabled the use of fluorescent based molecular localization tools to study whole cell structural biology. Machine learning based analysis of super-resolution data offers tremendous potential for discovery of new biology, that by definition is not known and lacks ground truth. Herein, we describe the application of weakly supervised learning paradigms to super-resolution microscopy and its potential to enable the accelerated exploration of the molecular architecture of subcellular macromolecules and organelles.

Scientists use super-resolution microscopy to study previously undiscovered cellular worlds, revealing nanometre-scale details inside cells. The method revolutionised light microscopy and earned its inventors the 2014 Nobel Prize in Chemistry. Single-molecule localisation microscopy (SMLM) is a type of super-resolution microscopy. It involves labelling proteins of interest with fluorescent molecules and using light to activate only a few molecules at a time. Using this method, multiple images of the same sample are acquired.

With super-resolution optical microscopy, it is now possible to observe molecular interactions in living cells. The obtained images have a very high spatial precision but their overall quality can vary a lot depending on the structure of interest and the imaging parameters. Moreover, evaluating this quality is often difficult for non-expert users. In this work, we tackle the problem of learning the quality function of super-resolution images from scores provided by experts. More specifically, we are proposing a system based on a deep neural network that can provide a quantitative quality measure of a STED image of neuronal structures given as input. We conduct a user study in order to evaluate the quality of the predictions of the neural network against those of a human expert. Results show the potential while highlighting some of the limits of the proposed approach.