Performance Review of Retraining and Transfer Learning of DeLTA2 for Image Segmentation for Pseudomonas Fluorescens SBW25

Beate Gericke, Finn Degner, Tom Hüttmann, Sören Werth, Carsten Fortmann-Grote

2024

Abstract

High throughput microscopy imaging yields vast amount of image data, e.g. in microbiology, cell biology, and medical diagnostics calling for automated analysis methods. Despite recent progress in employing deep neural networks to image segmentation in a supervised learning setting, these models often do not meet the performance requirement when used without model refinement in particular when cells accumulate and overlap in the image plane. Here, we analyse segmentation performance gains obtained through retraining and through transfer learning using a curated dataset of phase contrast microscopy images taken of individual cells and cell accumulations of Pseudomonas fluorescens SBW25. Both methods yield significant improvement over the baseline model DeLTA2 (O’Conner et al. PLOS Comp. Biol 18, e1009797 (2022)) in intersection–over–union and balanced accuracy test metrics. We demonstrate that (computationally cheaper) transfer learning of only 25% of neural network layers yields the same improvement over the baseline as a complete retraining run. Furthermore, we achieve highest performance boosts when the training data contains only well separated cells even though the test split may contain cell accumulations. This opens up the possibility for a semi–automated segmentation workflow combining feature extraction techniques for ground truth mask generation from low complexity images and supervised learning for the more complex data.

Paper Citation

in Harvard Style

Gericke B., Degner F., Hüttmann T., Werth S. and Fortmann-Grote C. (2024). Performance Review of Retraining and Transfer Learning of DeLTA2 for Image Segmentation for Pseudomonas Fluorescens SBW25. In Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOIMAGING; ISBN 978-989-758-688-0, SciTePress, pages 273-280. DOI: 10.5220/0012316300003657

in Bibtex Style

@conference{bioimaging24,
author={Beate Gericke and Finn Degner and Tom Hüttmann and Sören Werth and Carsten Fortmann-Grote},
title={Performance Review of Retraining and Transfer Learning of DeLTA2 for Image Segmentation for Pseudomonas Fluorescens SBW25},
booktitle={Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOIMAGING},
year={2024},
pages={273-280},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012316300003657},
isbn={978-989-758-688-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOIMAGING
TI - Performance Review of Retraining and Transfer Learning of DeLTA2 for Image Segmentation for Pseudomonas Fluorescens SBW25
SN - 978-989-758-688-0
AU - Gericke B.
AU - Degner F.
AU - Hüttmann T.
AU - Werth S.
AU - Fortmann-Grote C.
PY - 2024
SP - 273
EP - 280
DO - 10.5220/0012316300003657
PB - SciTePress