Towards Interpretable Classification of Leukocytes based on Deep Learning

Stefan Röhrl, Johannes Groll, Manuel Lengl, Simon Schumann, Christian Klenk, Dominik Heim, Martin Knopp, Oliver Hayden, Klaus Diepold

Keywords: Interpretable Machine Learning, Confidence Calibration, Visual Explanation, Quantitative Phase Imaging, Biomedical Imaging, Leukocyte Differentiation

TL;DR: This work investigates the interpretability of deep learning classifiers for emerging in-vitro diagnostics of leukocytes, with a view to establishing them in professional healthcare applications.

Abstract: Label-free approaches are attractive in cytological imaging due to their flexibility and cost efficiency. They are supported by machine learning methods, which, despite the lack of labeling and the associated lower contrast, can classify cells with high accuracy where the human observer has a little chance to discriminate cells. In order to better integrate these workflows into the clinical decision making process, this work investigates the calibration of confidence estimation for the automated classification of leukocytes. In addition, different visual explanation approaches are compared, which should bring machine decision making closer to professional healthcare applications. Furthermore, we were able to identify general detection patterns in neural networks and demonstrate the utility of the presented approaches in different scenarios of blood cell analysis.

Submission Number: 14