EvoSeg: Automated Electron Microscopy Segmentation through Random Forests and Evolutionary Optimization

Abstract

Electron Microscopy Maps are key in the study of bio-molecular structures, ranging from borderline atomic level to the sub-cellular range. These maps describe the envelopes that cover possibly a very large number of proteins that form molecular machines within the cell. Within those envelopes, we are interested to find what regions correspond to specific proteins so that we can understand how they function, and design drugs that can enhance or suppress a process that they are involved in, along with other experimental purposes. A classic approach by which we can begin the exploration of map regions is to apply a segmentation algorithm. This yields a mask where each voxel in 3D space is assigned an identifier that maps it to a segment; an ideal segmentation would map each segment to one protein unit, which is rarely the case. In this work, we present a method that uses bio-inspired optimization, through an Evolutionary-Optimized Segmentation algorithm, to iteratively improve upon baseline segments obtained from a classical approach, called watershed segmentation. The cost function used by the evolutionary optimization is based on an ideal segmentation classifier trained as part of this development, which uses basic structural information available to scientists, such as the number of expected units, volume and topology. We show that a basic initial segmentation with the additional information allows our evolutionary method to find better segmentation results, compared to the baseline generated by the watershed.

Impact of Training Data, Ground Truth and Shape Variability in the Deep Learning-Based Semantic Segmentation of HeLa Cells Observed with Electron Microscopy

“…That is, regions are considered homogeneous when they belong to the same catchment basin through which idealized “rain” would flow toward a “lake”. The watershed provides a partition for very different thresholding, and thus is a very useful step of many segmentation algorithms [ 45 , 46 ]. Active contours define a curve or “snake”, which iteratively evolves to detect objects in an image based on constraints within the image itself [ 47 ].…”

Exploiting volume electron microscopy to investigate structural plasticity and stability of the postsynaptic compartment of central synapses

“…In recent years, vEM confirmed an observation about the geometry of the PSD that was already reported from TEM analyses of central synapses (Toni et al, 2001;Morales et al, 2011 and references therein); the PSD is not always a simple discoidal structure whose shape can be simply described with length, thickness and volume, but instead it can undergo morphological changes, which reflect different functional states of the synapse (Hering and Sheng, 2001). To use the geometry of this important component of the postsynapse to quantitatively characterize neuronal connectivity across large portions of the neuropil, huge vEM dataset were generated, and the need to analyze this large amount of data led to the development of automatic software for the segmentation and reconstruction (Morales et al, 2011;Cardona et al, 2012;Berg et al, 2019;Zumbado-Corrales and Esquivel-Rodríguez, 2021), which, in some cases reduced the spatial accuracy of the analysis.…”

Bioinspired Intelligence II

“…Zumbado-Corrales and Esquivel-Rodríguez [ 3 ] present a bio-inspired computation optimization method, an Evolutionary-Optimized Segmentation algorithm, that iteratively improves baseline segments obtained from a classical approach called watershed segmentation. Moreover, they included a cost function based on an ideal segmentation classifier trained as part of their development, which uses basic structural information available to scientists, such as the number of expected units, volume, and topology.…”