A4 Refereed article in a conference publication
Detection of tumor cell spheroids from co-cultures using phase contrast images and machine learning approach
Authors: Bayramoglu N, Kaakinen M, Eklund L, Akerfelt M, Nees M, Kannala J, Heikkila J
Editors: IEEE
Conference name: International Conference on Pattern Recognition (ICPR)
Publication year: 2014
Journal: International Conference on Pattern Recognition
Book title : 2014 22nd International Conference on Pattern Recognition (ICPR)
Journal name in source: 2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)
Journal acronym: INT C PATT RECOG
First page : 3345
Last page: 3350
Number of pages: 6
eISBN: 978-1-4799-5209-0
ISSN: 1051-4651
DOI: https://doi.org/10.1109/ICPR.2014.576
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 superpixels. 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.
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 superpixels. 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.
UTU Research Portal