YeastFormer: An End-to-End Instance Segmentation Approach for Yeast Cells in Microstructure Environment

Khola Naseem, Khola Naseem, Nabeel Khalid, Nabeel Khalid, Lea Bertgen, Johannes M. Herrmann, Andreas Dengel, Andreas Dengel, Sheraz Ahmed

2025

Abstract

Cell segmentation is a crucial task, especially in microstructured environments commonly used in synthetic biology. Segmenting cells in these environments becomes particularly challenging when the cells and the surrounding traps share similar characteristics. While deep learning-based methods have shown success in cell segmentation, limited progress has been made in segmenting yeast cells within such complex environments. Most current approaches rely on traditional machine learning techniques. To address this challenge, the study proposed a transfer-based instance segmentation approach to tackle both cell and trap segmentation in mi-crostructured environments. The attention-based mechanism in the model’s backbone enables a more precise focus on key features, leading to improved segmentation accuracy. The proposed approach outperforms existing state-of-the-art methods, achieving a 5% improvement in terms of Intersection over Union (IoU) for the segmentation of both cells and traps in microscopic images.

Paper Citation

in Harvard Style

Naseem K., Khalid N., Bertgen L., Herrmann J., Dengel A. and Ahmed S. (2025). YeastFormer: An End-to-End Instance Segmentation Approach for Yeast Cells in Microstructure Environment. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 407-417. DOI: 10.5220/0013169400003890

in Bibtex Style

@conference{icaart25,
author={Khola Naseem and Nabeel Khalid and Lea Bertgen and Johannes Herrmann and Andreas Dengel and Sheraz Ahmed},
title={YeastFormer: An End-to-End Instance Segmentation Approach for Yeast Cells in Microstructure Environment},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={407-417},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013169400003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - YeastFormer: An End-to-End Instance Segmentation Approach for Yeast Cells in Microstructure Environment
SN - 978-989-758-737-5
AU - Naseem K.
AU - Khalid N.
AU - Bertgen L.
AU - Herrmann J.
AU - Dengel A.
AU - Ahmed S.
PY - 2025
SP - 407
EP - 417
DO - 10.5220/0013169400003890
PB - SciTePress