Learning to Become an Expert: Deep Networks Applied To Super-Resolution Microscopy
This work addresses the difficulty for non-expert users in evaluating the quality of super-resolution microscopy images, which is an incremental improvement in the domain of biomedical imaging.
The paper tackles the problem of learning a quality function for super-resolution microscopy images from expert scores, proposing a deep neural network to provide quantitative quality measures for STED images of neuronal structures. Results from a user study show the potential of the approach while highlighting its limitations.
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.