Automatic MRI brain segmentation using local features, self-organizing maps, and watershed

Mehryar Emambakhsh, Mohammad Hossein Sedaaghi

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

Image segmentation is the process of partitioning an input image into non-overlapping/disjoint regions. Various methods have been used for image segmentation. Among these methods, watershed-based algorithms have been widely utilized due to their fast computational speed. However, their sensitivity to noise, and also over-segmentation, has made watershed approaches unsuitable for noisy images. In this paper, a novel method for MRI segmentation is proposed. For this purposed, a simple and fast feature extraction method is used. Then, the feature space, is clustered by Self-Organizing Map Neural Networks (SOMNN). After that, an edge map is set up from the clustering result. Finally, watershed transformation is utilized on the edge map. Our algorithm is robust against noise. Although watershed transformation is used in our approach, a region merging and denoising algorithms are not utilized as pre- and post- processing, respectively. This significantly improves the segmentation speed.
Original languageEnglish
Pages123-128
Number of pages6
DOIs
Publication statusPublished - 2009
EventIEEE International Conference on Signal and Image Processing Applications (ICSIPA) - Kuala Lumpur, Malaysia
Duration: 18 Nov 200919 Nov 2009

Conference

ConferenceIEEE International Conference on Signal and Image Processing Applications (ICSIPA)
CountryMalaysia
CityKuala Lumpur
Period18/11/0919/11/09

Fingerprint

Self organizing maps
Watersheds
Magnetic resonance imaging
Brain
Image segmentation
Merging
Feature extraction
Neural networks
Processing

Cite this

Emambakhsh, M., & Sedaaghi, M. H. (2009). Automatic MRI brain segmentation using local features, self-organizing maps, and watershed. 123-128. Paper presented at IEEE International Conference on Signal and Image Processing Applications (ICSIPA), Kuala Lumpur, Malaysia. https://doi.org/10.1109/ICSIPA.2009.5478631

Automatic MRI brain segmentation using local features, self-organizing maps, and watershed. / Emambakhsh, Mehryar; Sedaaghi, Mohammad Hossein.

2009. 123-128 Paper presented at IEEE International Conference on Signal and Image Processing Applications (ICSIPA), Kuala Lumpur, Malaysia.

Research output: Contribution to conferencePaper

Emambakhsh, M & Sedaaghi, MH 2009, 'Automatic MRI brain segmentation using local features, self-organizing maps, and watershed' Paper presented at IEEE International Conference on Signal and Image Processing Applications (ICSIPA), Kuala Lumpur, Malaysia, 18/11/09 - 19/11/09, pp. 123-128. https://doi.org/10.1109/ICSIPA.2009.5478631
Emambakhsh M, Sedaaghi MH. Automatic MRI brain segmentation using local features, self-organizing maps, and watershed. 2009. Paper presented at IEEE International Conference on Signal and Image Processing Applications (ICSIPA), Kuala Lumpur, Malaysia. https://doi.org/10.1109/ICSIPA.2009.5478631
Emambakhsh, Mehryar ; Sedaaghi, Mohammad Hossein. / Automatic MRI brain segmentation using local features, self-organizing maps, and watershed. Paper presented at IEEE International Conference on Signal and Image Processing Applications (ICSIPA), Kuala Lumpur, Malaysia.6 p.
@conference{2bde1d576b4f480fbf0f9458a4bb88d4,
title = "Automatic MRI brain segmentation using local features, self-organizing maps, and watershed",
abstract = "Image segmentation is the process of partitioning an input image into non-overlapping/disjoint regions. Various methods have been used for image segmentation. Among these methods, watershed-based algorithms have been widely utilized due to their fast computational speed. However, their sensitivity to noise, and also over-segmentation, has made watershed approaches unsuitable for noisy images. In this paper, a novel method for MRI segmentation is proposed. For this purposed, a simple and fast feature extraction method is used. Then, the feature space, is clustered by Self-Organizing Map Neural Networks (SOMNN). After that, an edge map is set up from the clustering result. Finally, watershed transformation is utilized on the edge map. Our algorithm is robust against noise. Although watershed transformation is used in our approach, a region merging and denoising algorithms are not utilized as pre- and post- processing, respectively. This significantly improves the segmentation speed.",
author = "Mehryar Emambakhsh and Sedaaghi, {Mohammad Hossein}",
year = "2009",
doi = "10.1109/ICSIPA.2009.5478631",
language = "English",
pages = "123--128",
note = "IEEE International Conference on Signal and Image Processing Applications (ICSIPA) ; Conference date: 18-11-2009 Through 19-11-2009",

}

TY - CONF

T1 - Automatic MRI brain segmentation using local features, self-organizing maps, and watershed

AU - Emambakhsh, Mehryar

AU - Sedaaghi, Mohammad Hossein

PY - 2009

Y1 - 2009

N2 - Image segmentation is the process of partitioning an input image into non-overlapping/disjoint regions. Various methods have been used for image segmentation. Among these methods, watershed-based algorithms have been widely utilized due to their fast computational speed. However, their sensitivity to noise, and also over-segmentation, has made watershed approaches unsuitable for noisy images. In this paper, a novel method for MRI segmentation is proposed. For this purposed, a simple and fast feature extraction method is used. Then, the feature space, is clustered by Self-Organizing Map Neural Networks (SOMNN). After that, an edge map is set up from the clustering result. Finally, watershed transformation is utilized on the edge map. Our algorithm is robust against noise. Although watershed transformation is used in our approach, a region merging and denoising algorithms are not utilized as pre- and post- processing, respectively. This significantly improves the segmentation speed.

AB - Image segmentation is the process of partitioning an input image into non-overlapping/disjoint regions. Various methods have been used for image segmentation. Among these methods, watershed-based algorithms have been widely utilized due to their fast computational speed. However, their sensitivity to noise, and also over-segmentation, has made watershed approaches unsuitable for noisy images. In this paper, a novel method for MRI segmentation is proposed. For this purposed, a simple and fast feature extraction method is used. Then, the feature space, is clustered by Self-Organizing Map Neural Networks (SOMNN). After that, an edge map is set up from the clustering result. Finally, watershed transformation is utilized on the edge map. Our algorithm is robust against noise. Although watershed transformation is used in our approach, a region merging and denoising algorithms are not utilized as pre- and post- processing, respectively. This significantly improves the segmentation speed.

UR - http://dx.doi.org/10.1109/ICSIPA.2009.5478631

U2 - 10.1109/ICSIPA.2009.5478631

DO - 10.1109/ICSIPA.2009.5478631

M3 - Paper

SP - 123

EP - 128

ER -