Proceedings on Automation in Medical Engineering
Vol. 1 No. 1 (2020): Proc AUTOMED

General procedures and methods, ID 025

A task-dependent active learning method for axon segmentation with CNNs

Main Article Content

Philipp Grüning (Institute for Neuro- and Bioinformatics, University of Lübeck, Lübeck, Germany), Alex Palumbo , Marietta Zille , Erhardt Barth (Institute for Neuro- and Bioinformatics, Universität zu Lübeck, Lübeck, Germany), Amir Madany Mamlouk (Institute for Neuro- and Bioinformatics, Universität zu Lübeck, Lübeck, Germany)

Copyright (c) 2020 Proceedings on Automation in Medical Engineering

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Convolutional neural networks (CNNs) can provide reliable segmentation results on biomedical images. However, they can only develop their full potential with a representative dataset. Unfortunately, a large dataset is hard to create in biomedical research, since labeling images is time consuming and requires expert knowledge. Active learning seeks to determine those images that will yield the best results, which effectively reduces labeling cost. We present an active learning method for the stepwise identification of images that should be labeled next and test this method on a axon segmentation dataset. We outperform a baseline and a state-of-the-art method.

Article Details