Super-resolution using Sparse Representations over Learned Dictionaries: Reconstruction of Brain Structure using Electron Microscopy
This addresses the challenge of high-throughput, high-resolution brain imaging for neuroscience, representing an incremental advance by applying existing compressive sensing and unsupervised learning techniques to a specific domain.
The paper tackled the problem of reconstructing neuronal circuits at the synapse level by computationally achieving high depth-resolution in electron microscopy without sacrificing throughput, using sparse representations over learned dictionaries to enable reconstruction from as few as 5 tomographic views.
A central problem in neuroscience is reconstructing neuronal circuits on the synapse level. Due to a wide range of scales in brain architecture such reconstruction requires imaging that is both high-resolution and high-throughput. Existing electron microscopy (EM) techniques possess required resolution in the lateral plane and either high-throughput or high depth resolution but not both. Here, we exploit recent advances in unsupervised learning and signal processing to obtain high depth-resolution EM images computationally without sacrificing throughput. First, we show that the brain tissue can be represented as a sparse linear combination of localized basis functions that are learned using high-resolution datasets. We then develop compressive sensing-inspired techniques that can reconstruct the brain tissue from very few (typically 5) tomographic views of each section. This enables tracing of neuronal processes and, hence, high throughput reconstruction of neural circuits on the level of individual synapses.