Applications of multiscale segmentation and classification approaches to histological images
Image segmentation and object recognition are important applications of signal processing. While there are no generic solutions of these problems several classes of algorithms provide acceptable results to most of the applied problems. Common approaches range from intensity based to purely geometry based. The lecture will give overview of some of the most widely used approaches with emphasis on scale spaces and wavelets. In particular approaches based on the Laplacian and Fractional Laplacian operators for edge detection will be presented. Selected applications of these approaches include segmentation of nuclei, cell bodies and tissue textures. Implementations of the various filters will be demonstrated using the popular image analysis platform ImageJ. As a second step of such analysis pipeline some classification problems in feature space will be outlined including Gaussian mixture modeling, support vector machines and active learning. Presented approaches have been used in analysis of neuroinflammation, electron-microscopic images and local motion estimation in time lapse images.
Acknowledgements
The work has been supported in part by a grant from Research Fund - Flanders (FWO), contract number 0880.212.840.
References
Duits R, M. Felsberg, L. Florack, and B. Platel. (2003). Alpha-scale spaces on a bounded domain. Scale Space Methods in Computer Vision, 494- 510. Springer.
Prodanov D (2013). Open source image analysis software toolboxes for microscopic applications. Front. Neuroinform. Conference Abstract: Imaging the brain at different scales: How to integrate multi-scale structural information?. doi: 10.3389/conf.fninf.2013.10.00005
Lindeberg, T. (1994). Scale-space theory: A basic tool for analysing structures at different scales. J App Stat. 21 (2): 224–270.
Weickert J. (1998). Anisotropic Diffusion in Image Processing. ECMI Series. Teubner-Verlag, Stuttgart.
Keywords:
Scale space theory,
wavelet analysis,
segmentation,
Classification,
machine learning applied to neuroscience
Conference:
Second Belgian Neuroinformatics Congress, Leuven, Belgium, 4 Dec - 4 Dec, 2015.
Presentation Type:
Invited Lecture
Topic:
Methods and Modeling
Citation:
Prodanov
D
(2015). Applications of multiscale segmentation and classification approaches to histological images.
Front. Neuroinform.
Conference Abstract:
Second Belgian Neuroinformatics Congress.
doi: 10.3389/conf.fninf.2015.19.00002
Copyright:
The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers.
They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.
The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.
Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.
For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.
Received:
31 Oct 2015;
Published Online:
17 Nov 2015.
*
Correspondence:
Dr. Dimiter Prodanov, IMEC, Leuven, 3001, Belgium, dimiterpp@gmail.com