English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Automated analysis of electron microscopy datasets poses multiple challenges,such as limitation in the size of the training dataset, variation in datadistribution induced by variation in sample quality and experiment conditions,etc. It is crucial for the trained model to continue to provide acceptablesegmentation/classification performance on new data, and quantify theuncertainty associated with its predictions. Among the broad applications ofmachine learning, various approaches have been adopted to quantify uncertainty,such as Bayesian modeling, Monte Carlo dropout, ensembles, etc. With the aim ofaddressing the challenges specific to the data domain of electron microscopy,two different types of ensembles of pre-trained neural networks wereimplemented in this work. The ensembles performed semantic segmentation of icecrystal within a two-phase mixture, thereby tracking its phase transformationto water. The first ensemble (EA) is composed of U-net style networks havingdifferent underlying architectures, whereas the second series of ensembles(ER-i) are composed of randomly initialized U-net style networks, wherein eachbase learner has the same underlying architecture 'i'. The encoders of the baselearners were pre-trained on the Imagenet dataset. The performance of EA and ERwere evaluated on three different metrics: accuracy, calibration, anduncertainty. It is seen that EA exhibits a greater classification accuracy andis better calibrated, as compared to ER. While the uncertainty quantificationof these two types of ensembles are comparable, the uncertainty scoresexhibited by ER were found to be dependent on the specific architecture of itsbase member ('i') and not consistently better than EA. Thus, the challengesposed for the analysis of electron microscopy datasets appear to be betteraddressed by an ensemble design like EA, as compared to an ensemble design likeER.

Ensemble of Pre-Trained Neural Networks for Segmentation and Quality Detection of Transmission Electron Microscopy Images