Deodato, Giacomo, Ball, Christopher and Zhang, Xian (2019) Bayesian Neural Networks for Cellular Image Classification and Uncertainty Analysis. www.biorxiv.org.

Abstract

Over the last decades, deep learning models have rapidly gained popularity for their ability to
achieve state-of-the-art performances in different inference settings. Deep neural networks
have been applied to an increasing number of problems spanning different domains of
application. Novel applications define a new set of requirements that transcend accurate
predictions and depend on uncertainty measures. The aims of this study are to implement
Bayesian neural networks and use the corresponding uncertainty estimates to perform predictions
and dataset analysis. We identify two main advantages in modeling the predictive
uncertainty of deep neural networks performing classification tasks. The first is the possibility
to discard highly uncertain predictions to be able to guarantee a higher accuracy of
the remaining predictions. The second is the identification of unfamiliar patterns in the data
that correspond to outliers in the model representation of the training data distribution. Such
outliers can be further characterized as either corrupted observations or data belonging to
different domains. Both advantages are well demonstrated with the benchmark datasets.
Furthermore we apply the Bayesian approach to a biomedical imaging dataset where cancer
cells are treated with diverse drugs, and show how one can increase classification accuracy
and identify noise in the ground truth labels with uncertainty analysis.

Item Type:	Article
Date Deposited:	24 Dec 2019 00:45
Last Modified:	24 Dec 2019 00:45
URI:	https://oak.novartis.com/id/eprint/41406