Detection of Tumor Cell Spheroids from Co-cultures Using Phase Contrast Images and Machine Learning Approach

Neslihan Bayramoglu, Mika Kaakinen, Lauri Eklund, Malin Åkerfelt, Matthias Nees, Juho Kannala, Janne Heikkilä

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

4 Citations (Scopus)

Abstract

Automated image analysis is demanded in cell biology and drug development research. The type of microscopy is one of the considerations in the trade-offs between experimental setup, image acquisition speed, molecular labelling, resolution and quality of images. In many cases, phase contrast imaging gets higher weights in this optimization. And it comes at the price of reduced image quality in imaging 3D cell cultures. For such data, the existing state-of-the-art computer vision methods perform poorly in segmenting specific cell type. Low SNR, clutter and occlusions are basic challenges for blind segmentation approaches. In this study we propose an automated method, based on a learning framework, for detecting particular cell type in cluttered 2D phase contrast images of 3D cell cultures that overcomes those challenges. It depends on local features defined over super pixels. The method learns appearance based features, statistical features, textural features and their combinations. Also, the importance of each feature is measured by employing Random Forest classifier. Experiments show that our approach does not depend on training data and the parameters
Original languageEnglish
Title of host publicationProceedings
Subtitle of host publication22nd International Conference on Pattern Recognition, ICPR 2014
PublisherIEEE Institute of Electrical and Electronic Engineers
Pages3345-3350
ISBN (Print)978-1-4799-5209-0
DOIs
Publication statusPublished - 2014
MoE publication typeA4 Article in a conference publication
Event22nd International Conference on Pattern Recognition, ICPR 2014 - Stockholm, Sweden
Duration: 24 Aug 201428 Aug 2014

Conference

Conference22nd International Conference on Pattern Recognition, ICPR 2014
Abbreviated titleICPR 2014
CountrySweden
CityStockholm
Period24/08/1428/08/14

Fingerprint

Cell culture
Learning systems
Tumors
Cells
Cytology
Imaging techniques
Image acquisition
Labeling
Image analysis
Image quality
Computer vision
Microscopic examination
Classifiers
Pixels
Experiments

Cite this

Bayramoglu, N., Kaakinen, M., Eklund, L., Åkerfelt, M., Nees, M., Kannala, J., & Heikkilä, J. (2014). Detection of Tumor Cell Spheroids from Co-cultures Using Phase Contrast Images and Machine Learning Approach. In Proceedings: 22nd International Conference on Pattern Recognition, ICPR 2014 (pp. 3345-3350). IEEE Institute of Electrical and Electronic Engineers . https://doi.org/10.1109/ICPR.2014.576
Bayramoglu, Neslihan ; Kaakinen, Mika ; Eklund, Lauri ; Åkerfelt, Malin ; Nees, Matthias ; Kannala, Juho ; Heikkilä, Janne. / Detection of Tumor Cell Spheroids from Co-cultures Using Phase Contrast Images and Machine Learning Approach. Proceedings: 22nd International Conference on Pattern Recognition, ICPR 2014. IEEE Institute of Electrical and Electronic Engineers , 2014. pp. 3345-3350
@inproceedings{64a511a8c72345d8aafecdf1614f88f5,
title = "Detection of Tumor Cell Spheroids from Co-cultures Using Phase Contrast Images and Machine Learning Approach",
abstract = "Automated image analysis is demanded in cell biology and drug development research. The type of microscopy is one of the considerations in the trade-offs between experimental setup, image acquisition speed, molecular labelling, resolution and quality of images. In many cases, phase contrast imaging gets higher weights in this optimization. And it comes at the price of reduced image quality in imaging 3D cell cultures. For such data, the existing state-of-the-art computer vision methods perform poorly in segmenting specific cell type. Low SNR, clutter and occlusions are basic challenges for blind segmentation approaches. In this study we propose an automated method, based on a learning framework, for detecting particular cell type in cluttered 2D phase contrast images of 3D cell cultures that overcomes those challenges. It depends on local features defined over super pixels. The method learns appearance based features, statistical features, textural features and their combinations. Also, the importance of each feature is measured by employing Random Forest classifier. Experiments show that our approach does not depend on training data and the parameters",
author = "Neslihan Bayramoglu and Mika Kaakinen and Lauri Eklund and Malin {\AA}kerfelt and Matthias Nees and Juho Kannala and Janne Heikkil{\"a}",
year = "2014",
doi = "10.1109/ICPR.2014.576",
language = "English",
isbn = "978-1-4799-5209-0",
pages = "3345--3350",
booktitle = "Proceedings",
publisher = "IEEE Institute of Electrical and Electronic Engineers",
address = "United States",

}

Bayramoglu, N, Kaakinen, M, Eklund, L, Åkerfelt, M, Nees, M, Kannala, J & Heikkilä, J 2014, Detection of Tumor Cell Spheroids from Co-cultures Using Phase Contrast Images and Machine Learning Approach. in Proceedings: 22nd International Conference on Pattern Recognition, ICPR 2014. IEEE Institute of Electrical and Electronic Engineers , pp. 3345-3350, 22nd International Conference on Pattern Recognition, ICPR 2014, Stockholm, Sweden, 24/08/14. https://doi.org/10.1109/ICPR.2014.576

Detection of Tumor Cell Spheroids from Co-cultures Using Phase Contrast Images and Machine Learning Approach. / Bayramoglu, Neslihan; Kaakinen, Mika; Eklund, Lauri; Åkerfelt, Malin; Nees, Matthias; Kannala, Juho; Heikkilä, Janne.

Proceedings: 22nd International Conference on Pattern Recognition, ICPR 2014. IEEE Institute of Electrical and Electronic Engineers , 2014. p. 3345-3350.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Detection of Tumor Cell Spheroids from Co-cultures Using Phase Contrast Images and Machine Learning Approach

AU - Bayramoglu, Neslihan

AU - Kaakinen, Mika

AU - Eklund, Lauri

AU - Åkerfelt, Malin

AU - Nees, Matthias

AU - Kannala, Juho

AU - Heikkilä, Janne

PY - 2014

Y1 - 2014

N2 - Automated image analysis is demanded in cell biology and drug development research. The type of microscopy is one of the considerations in the trade-offs between experimental setup, image acquisition speed, molecular labelling, resolution and quality of images. In many cases, phase contrast imaging gets higher weights in this optimization. And it comes at the price of reduced image quality in imaging 3D cell cultures. For such data, the existing state-of-the-art computer vision methods perform poorly in segmenting specific cell type. Low SNR, clutter and occlusions are basic challenges for blind segmentation approaches. In this study we propose an automated method, based on a learning framework, for detecting particular cell type in cluttered 2D phase contrast images of 3D cell cultures that overcomes those challenges. It depends on local features defined over super pixels. The method learns appearance based features, statistical features, textural features and their combinations. Also, the importance of each feature is measured by employing Random Forest classifier. Experiments show that our approach does not depend on training data and the parameters

AB - Automated image analysis is demanded in cell biology and drug development research. The type of microscopy is one of the considerations in the trade-offs between experimental setup, image acquisition speed, molecular labelling, resolution and quality of images. In many cases, phase contrast imaging gets higher weights in this optimization. And it comes at the price of reduced image quality in imaging 3D cell cultures. For such data, the existing state-of-the-art computer vision methods perform poorly in segmenting specific cell type. Low SNR, clutter and occlusions are basic challenges for blind segmentation approaches. In this study we propose an automated method, based on a learning framework, for detecting particular cell type in cluttered 2D phase contrast images of 3D cell cultures that overcomes those challenges. It depends on local features defined over super pixels. The method learns appearance based features, statistical features, textural features and their combinations. Also, the importance of each feature is measured by employing Random Forest classifier. Experiments show that our approach does not depend on training data and the parameters

U2 - 10.1109/ICPR.2014.576

DO - 10.1109/ICPR.2014.576

M3 - Conference article in proceedings

SN - 978-1-4799-5209-0

SP - 3345

EP - 3350

BT - Proceedings

PB - IEEE Institute of Electrical and Electronic Engineers

ER -

Bayramoglu N, Kaakinen M, Eklund L, Åkerfelt M, Nees M, Kannala J et al. Detection of Tumor Cell Spheroids from Co-cultures Using Phase Contrast Images and Machine Learning Approach. In Proceedings: 22nd International Conference on Pattern Recognition, ICPR 2014. IEEE Institute of Electrical and Electronic Engineers . 2014. p. 3345-3350 https://doi.org/10.1109/ICPR.2014.576