Automatic tumor lesion detection and segmentation using modified winnow algorithm

N. Nabizadeh, M. Dorodch, Miroslav Kubat

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Automated recognition of brain tumors in magnetic resonance images (MRI) is a difficult procedure due to the variability and complexity of the location, size, shape, and texture of these lesions. Due to intensity similarities between brain lesions and normal tissues, most approaches make use of multi-spectral MRI images. However, the time, cost, and data process restrictions for collecting multi-spectral MRI necessitate developing a lesion detection and segmentation approach that can detect lesions using a single anatomical MRI image. In this paper, we present a fully automatic system, which is able to detect the MRI images that include tumor and to segment the tumor area. Fully anisotropic complex Morlet transform, and dual tree complex wavelet transform are introduced for tumor textural characterization. Perhaps most importantly, we propose a novel feature selection technique that is based on regularized Winnow algorithm. An active contour model implemented with selective binary and Gaussian filtering regularized level set (SBGFRLS) is used for final segmentation step. The experimental results on both simulated and real brain MRI data prove the efficacy of our technique in successfully segmenting brain tumor tissues with high accuracy and low computational complexity.

Original languageEnglish (US)
Title of host publicationProceedings - International Symposium on Biomedical Imaging
PublisherIEEE Computer Society
Pages71-74
Number of pages4
Volume2015-July
ISBN (Print)9781479923748
DOIs
StatePublished - Jul 21 2015
Event12th IEEE International Symposium on Biomedical Imaging, ISBI 2015 - Brooklyn, United States
Duration: Apr 16 2015Apr 19 2015

Other

Other12th IEEE International Symposium on Biomedical Imaging, ISBI 2015
CountryUnited States
CityBrooklyn
Period4/16/154/19/15

Fingerprint

Magnetic resonance
Tumors
Magnetic Resonance Spectroscopy
Brain
Neoplasms
Brain Neoplasms
Tissue
Wavelet Analysis
Wavelet transforms
Feature extraction
Computational complexity
Textures
Costs and Cost Analysis
Costs

Keywords

  • anisotropic complex Morlet transform
  • dual tree complex wavelet transform
  • magnetic resonance imaging
  • regularized Winnow algorithm
  • SBGFR level set
  • Tumor lesion detection/segmentation

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Nabizadeh, N., Dorodch, M., & Kubat, M. (2015). Automatic tumor lesion detection and segmentation using modified winnow algorithm. In Proceedings - International Symposium on Biomedical Imaging (Vol. 2015-July, pp. 71-74). [7163819] IEEE Computer Society. https://doi.org/10.1109/ISBI.2015.7163819

Automatic tumor lesion detection and segmentation using modified winnow algorithm. / Nabizadeh, N.; Dorodch, M.; Kubat, Miroslav.

Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July IEEE Computer Society, 2015. p. 71-74 7163819.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nabizadeh, N, Dorodch, M & Kubat, M 2015, Automatic tumor lesion detection and segmentation using modified winnow algorithm. in Proceedings - International Symposium on Biomedical Imaging. vol. 2015-July, 7163819, IEEE Computer Society, pp. 71-74, 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015, Brooklyn, United States, 4/16/15. https://doi.org/10.1109/ISBI.2015.7163819
Nabizadeh N, Dorodch M, Kubat M. Automatic tumor lesion detection and segmentation using modified winnow algorithm. In Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July. IEEE Computer Society. 2015. p. 71-74. 7163819 https://doi.org/10.1109/ISBI.2015.7163819
Nabizadeh, N. ; Dorodch, M. ; Kubat, Miroslav. / Automatic tumor lesion detection and segmentation using modified winnow algorithm. Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July IEEE Computer Society, 2015. pp. 71-74
@inproceedings{0a848459556a45f382b57c4f71a3e7cb,
title = "Automatic tumor lesion detection and segmentation using modified winnow algorithm",
abstract = "Automated recognition of brain tumors in magnetic resonance images (MRI) is a difficult procedure due to the variability and complexity of the location, size, shape, and texture of these lesions. Due to intensity similarities between brain lesions and normal tissues, most approaches make use of multi-spectral MRI images. However, the time, cost, and data process restrictions for collecting multi-spectral MRI necessitate developing a lesion detection and segmentation approach that can detect lesions using a single anatomical MRI image. In this paper, we present a fully automatic system, which is able to detect the MRI images that include tumor and to segment the tumor area. Fully anisotropic complex Morlet transform, and dual tree complex wavelet transform are introduced for tumor textural characterization. Perhaps most importantly, we propose a novel feature selection technique that is based on regularized Winnow algorithm. An active contour model implemented with selective binary and Gaussian filtering regularized level set (SBGFRLS) is used for final segmentation step. The experimental results on both simulated and real brain MRI data prove the efficacy of our technique in successfully segmenting brain tumor tissues with high accuracy and low computational complexity.",
keywords = "anisotropic complex Morlet transform, dual tree complex wavelet transform, magnetic resonance imaging, regularized Winnow algorithm, SBGFR level set, Tumor lesion detection/segmentation",
author = "N. Nabizadeh and M. Dorodch and Miroslav Kubat",
year = "2015",
month = "7",
day = "21",
doi = "10.1109/ISBI.2015.7163819",
language = "English (US)",
isbn = "9781479923748",
volume = "2015-July",
pages = "71--74",
booktitle = "Proceedings - International Symposium on Biomedical Imaging",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Automatic tumor lesion detection and segmentation using modified winnow algorithm

AU - Nabizadeh, N.

AU - Dorodch, M.

AU - Kubat, Miroslav

PY - 2015/7/21

Y1 - 2015/7/21

N2 - Automated recognition of brain tumors in magnetic resonance images (MRI) is a difficult procedure due to the variability and complexity of the location, size, shape, and texture of these lesions. Due to intensity similarities between brain lesions and normal tissues, most approaches make use of multi-spectral MRI images. However, the time, cost, and data process restrictions for collecting multi-spectral MRI necessitate developing a lesion detection and segmentation approach that can detect lesions using a single anatomical MRI image. In this paper, we present a fully automatic system, which is able to detect the MRI images that include tumor and to segment the tumor area. Fully anisotropic complex Morlet transform, and dual tree complex wavelet transform are introduced for tumor textural characterization. Perhaps most importantly, we propose a novel feature selection technique that is based on regularized Winnow algorithm. An active contour model implemented with selective binary and Gaussian filtering regularized level set (SBGFRLS) is used for final segmentation step. The experimental results on both simulated and real brain MRI data prove the efficacy of our technique in successfully segmenting brain tumor tissues with high accuracy and low computational complexity.

AB - Automated recognition of brain tumors in magnetic resonance images (MRI) is a difficult procedure due to the variability and complexity of the location, size, shape, and texture of these lesions. Due to intensity similarities between brain lesions and normal tissues, most approaches make use of multi-spectral MRI images. However, the time, cost, and data process restrictions for collecting multi-spectral MRI necessitate developing a lesion detection and segmentation approach that can detect lesions using a single anatomical MRI image. In this paper, we present a fully automatic system, which is able to detect the MRI images that include tumor and to segment the tumor area. Fully anisotropic complex Morlet transform, and dual tree complex wavelet transform are introduced for tumor textural characterization. Perhaps most importantly, we propose a novel feature selection technique that is based on regularized Winnow algorithm. An active contour model implemented with selective binary and Gaussian filtering regularized level set (SBGFRLS) is used for final segmentation step. The experimental results on both simulated and real brain MRI data prove the efficacy of our technique in successfully segmenting brain tumor tissues with high accuracy and low computational complexity.

KW - anisotropic complex Morlet transform

KW - dual tree complex wavelet transform

KW - magnetic resonance imaging

KW - regularized Winnow algorithm

KW - SBGFR level set

KW - Tumor lesion detection/segmentation

UR - http://www.scopus.com/inward/record.url?scp=84944316330&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944316330&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2015.7163819

DO - 10.1109/ISBI.2015.7163819

M3 - Conference contribution

SN - 9781479923748

VL - 2015-July

SP - 71

EP - 74

BT - Proceedings - International Symposium on Biomedical Imaging

PB - IEEE Computer Society

ER -