Source Apportionment of Soil Samples by the Combination of Two Neural Networks Based on Computer-Controlled Scanning Electron Microscopy

AbstractWith the growing importance of three-dimensional and very large field of view imaging, acquisition time becomes a serious bottleneck. Additionally, dose reduction is of importance when imaging material like biological tissue that is sensitive to electron radiation. Random sparse scanning can be used in the combination with image reconstruction techniques to reduce the acquisition time or electron dose in scanning electron microscopy. In this study, we demonstrate a workflow that includes data acquisition on a scanning electron microscope, followed by a sparse image reconstruction based on compressive sensing or alternatively using neural networks. Neuron structures are automatically segmented from the reconstructed images using deep learning techniques. We show that the average dwell time per pixel can be reduced by a factor of 2–3, thereby providing a real-life confirmation of previous results on simulated data in one of the key segmentation applications in connectomics and thus demonstrating the feasibility and benefit of random sparse scanning techniques for a specific real-world scenario.

Download Full-text

Automated diatom searching in the digital scanning electron microscopy images of drowning cases using the deep neural networks

International Journal of Legal Medicine ◽

10.1007/s00414-020-02392-z ◽

2020 ◽

Author(s):

Weimin Yu ◽

Ye Xue ◽

Rob Knoops ◽

Danyuan Yu ◽

Evgeniya Balmashnova ◽

...

Keyword(s):

Electron Microscopy ◽

Neural Networks ◽

Scanning Electron Microscopy ◽

Deep Neural Networks ◽

Digital Scanning ◽

Microscopy Images ◽

Scanning Electron

Download Full-text

Two new centric diatoms (Bacillariophyta) from the sub-Antarctic region

Phytotaxa ◽

10.11646/phytotaxa.394.1.2 ◽

2019 ◽

Vol 394 (1) ◽

pp. 50 ◽

Cited By ~ 2

Author(s):

BART VAN DE VIJVER ◽

VÁCLAV HOUK

Keyword(s):

Electron Microscopy ◽

Scanning Electron Microscopy ◽

Central Area ◽

Soil Samples ◽

Antarctic Region ◽

Diatom Flora ◽

Main Island ◽

Centric Diatoms ◽

Heard Island ◽

Scanning Electron

During a survey of the limno-terrestrial diatom flora of the sub-Antarctic region, two unknown melosiroid diatom taxa were observed in several shaded, damp cave (moss and soil) samples from Heard Island and Ile de la Possession, the main island of the Crozet Archipelago. Comparison with already known species from the genus Melosira and the recently described genera Arcanodiscus, Angusticopula and Ferocia, resulted in the description of both new taxa based on detailed light and scanning electron microscopy. A first species was described as Ferocia subantarctica sp. nov. and can be distinguished based on its numerous, narrow girdle bands, relatively weakly domed valves, a limited number of well-developed spines and a rather large, hyaline central area. The second species, Arcanodiscus desmetianus Van de Vijver sp. nov., can be recognized based on its solitary frustules, a series of parallel ridges surrounding the mantle and a hyaline central area that is only less than 50% of the total valve diameter. Both taxa are morphologically and ecologically characterized and compared with all known melosiroid taxa worldwide.

Download Full-text