Live Cell Stage Classification Using Deep Learning

Uma Mahesh R N, Kushal S M, Ponnanna K V, Sanjan B M, Vishnu S

2025

Abstract

Live cell imaging has transformed biological research, offering real-time insight into dynamic cellular processes. This project focuses on using deep learning techniques to automate the detection and classification of live cell stages, specifically distinguishing between the interphase and mitosis phases. Traditional methods, such as fluorescence microscopy and flow cytometry, are highly dependent on manual or semiautomated, time-intensive and error-prone approaches. Our proposed solution employs advanced deep learning architectures, including Sequential Convolutional Neural Network (SCNN), ResNet50, and EfficientNetB0, to overcome these limitations. The data set used comprises high-resolution images of nematode cells, preprocessed using resizing, normalization, and data augmentation techniques to ensure robust model training. The performance of each model is evaluated on the basis of metrics such as accuracy, positive predictive value (PPV), sensitivity, and the F1 score. In particular, EfficientNetB0 emerges as the model with the best performance, achieving a test accuracy of 98%, showcasing its superior ability to generalize in diverse data.

Paper Citation

in Harvard Style

Mahesh R N U., S M K., K V P., B M S. and S V. (2025). Live Cell Stage Classification Using Deep Learning. In Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT; ISBN 978-989-758-763-4, SciTePress, pages 414-421. DOI: 10.5220/0013593300004664

in Bibtex Style

@conference{incoft25,
author={Uma Mahesh R N and Kushal S M and Ponnanna K V and Sanjan B M and Vishnu S},
title={Live Cell Stage Classification Using Deep Learning},
booktitle={Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT},
year={2025},
pages={414-421},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013593300004664},
isbn={978-989-758-763-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT
TI - Live Cell Stage Classification Using Deep Learning
SN - 978-989-758-763-4
AU - Mahesh R N U.
AU - S M K.
AU - K V P.
AU - B M S.
AU - S V.
PY - 2025
SP - 414
EP - 421
DO - 10.5220/0013593300004664
PB - SciTePress