Deep learning enables fast and dense single-molecule localization with high accuracy. Original publication: Speiser A., Muller L.-R. More generally, DECODE shows the power of using numerical simulations to train neural networks to solve challenging analysis problems in the natural sciences.
ML SUPER RESOLUTION SOFTWARE
We believe that just by upgrading their analysis software to DECODE many labs performing single-molecule localization microscopy can improve their images, even on their existing datasets.
We built a software package which implements the DECODE algorithm and which is available online. Our work shows how a novel approach to an ostensibly simple problem like the localization of spots can result in considerable advantages. With DECODE many labs can improve their images As a result, networks trained to localize fluorophores on simulated data are then also able to do it on real images! Rather than training the network on real images, we used synthetic data that we generated by numerical simulation.īy carefully incorporating what we know about the microscope, the camera, and the molecules’ patterns of fluorescence, we achieve a close similarity between real data and simulations. We therefore used a method that has recently become popular for training neural networks in such situations, and which the group has also successfully used in other contexts. However, in our application, we do not know where exactly the fluorophores are. the desired network outputs, in our case the locations of the fluorophores. Training neural networks requires pairs of inputs and reference labels, i.e. To make this work, we had to solve several challenges. Our algorithm is based on deep learning: We use an artificial neural network which takes camera images as input, and produces predictions of the underlying fluorophore locations (See Figure 1). Therefore, prior to our development, one needed to make sure that only a few spots were visible in each image, which in turn resulted in long imaging times. However, this method has one major drawback: typically, achieving a high localization precision requires the spots to be well separated.
Subsequently, localizations from many such images are combined to reconstruct a super-resolved image.
ML SUPER RESOLUTION SERIES
One of these methods is single-molecule localization microscopy which circumvents the resolution limit with a simple trick: Instead of activating all fluorophores in the specimen at the same time, only a few fluorophores are randomly activated at each time point, resulting in a series of images with isolated spots that can be localized with high precision. Super-resolution microscopy methods overcome this fundamental limit. If two such light sources are too close to each other, their images blur into each other and they can no longer be distinguished from each other. When looking at tiny objects, for example a fluorescently labeled molecule, what we observe is a bright spot which is much bigger than the molecule itself. Like in other forms of light microscopy, the resolution that can be achieved this way is limited by the physical properties of light itself. Fluorescence microscopy measures the light emitted by so-called fluorophores that are attached to biological structures of interest. To understand the impact of this technology, let us first consider the limits of previously existing techniques. These methods revolutionised light microscopy and earned its inventors the 2014 Nobel Prize in Chemistry. It allows them, for example, to examine subcellular architecture and molecular interactions at the nanoscale. Scientists use super-resolution microscopy to study previously undiscovered cellular worlds.
0 kommentar(er)
