Abstract

In this paper, we propose sparse coding-based approaches for segmentation of tumor regions from magnetic resonance (MR) images. Sparse coding with data-adapted dictionaries has been successfully employed in several image recovery and vision problems. The proposed approaches obtain sparse codes for each pixel in brain MR images considering their intensity values and location information. Since it is trivial to obtain pixel-wise sparse codes, and combining multiple features in the sparse coding setup is not straight-forward, we propose to perform sparse coding in a high-dimensional feature space where non-linear similarities can be effectively modeled. We use the training data from expert-segmented images to obtain kernel dictionaries with the kernel K-lines clustering procedure. For a test image, sparse codes are computed with these kernel dictionaries, and they are used to identify the tumor regions. This approach is completely automated, and does not require user intervention to initialize the tumor regions in a test image. Furthermore, a low complexity segmentation approach based on kernel sparse codes, which allows the user to initialize the tumor region, is also presented. Results obtained with both the proposed approaches are validated against manual segmentation by an expert radiologist, and it is shown that proposed methods lead to accurate tumor identification.

Original languageEnglish (US)
Article number1460004
JournalInternational Journal on Artificial Intelligence Tools
Volume23
Issue number3
DOIs
StatePublished - 2014

Fingerprint

Tumors
Magnetic resonance
Glossaries
Pixels
Brain
Recovery

Keywords

  • dictionary learning
  • kernel methods
  • MRI
  • sparse representations
  • tumor segmentation

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Kernel sparse models for automated tumor segmentation. / Thiagarajan, Jayaraman J.; Ramamurthy, Karthikeyan Natesan; Rajan, Deepta; Spanias, Andreas; Puri, Anup; Frakes, David.

In: International Journal on Artificial Intelligence Tools, Vol. 23, No. 3, 1460004, 2014.

Research output: Contribution to journalArticle

Thiagarajan, Jayaraman J. ; Ramamurthy, Karthikeyan Natesan ; Rajan, Deepta ; Spanias, Andreas ; Puri, Anup ; Frakes, David. / Kernel sparse models for automated tumor segmentation. In: International Journal on Artificial Intelligence Tools. 2014 ; Vol. 23, No. 3.
@article{4d33ccb980e64b988799c496d276d4d8,
title = "Kernel sparse models for automated tumor segmentation",
abstract = "In this paper, we propose sparse coding-based approaches for segmentation of tumor regions from magnetic resonance (MR) images. Sparse coding with data-adapted dictionaries has been successfully employed in several image recovery and vision problems. The proposed approaches obtain sparse codes for each pixel in brain MR images considering their intensity values and location information. Since it is trivial to obtain pixel-wise sparse codes, and combining multiple features in the sparse coding setup is not straight-forward, we propose to perform sparse coding in a high-dimensional feature space where non-linear similarities can be effectively modeled. We use the training data from expert-segmented images to obtain kernel dictionaries with the kernel K-lines clustering procedure. For a test image, sparse codes are computed with these kernel dictionaries, and they are used to identify the tumor regions. This approach is completely automated, and does not require user intervention to initialize the tumor regions in a test image. Furthermore, a low complexity segmentation approach based on kernel sparse codes, which allows the user to initialize the tumor region, is also presented. Results obtained with both the proposed approaches are validated against manual segmentation by an expert radiologist, and it is shown that proposed methods lead to accurate tumor identification.",
keywords = "dictionary learning, kernel methods, MRI, sparse representations, tumor segmentation",
author = "Thiagarajan, {Jayaraman J.} and Ramamurthy, {Karthikeyan Natesan} and Deepta Rajan and Andreas Spanias and Anup Puri and David Frakes",
year = "2014",
doi = "10.1142/S0218213014600045",
language = "English (US)",
volume = "23",
journal = "International Journal on Artificial Intelligence Tools",
issn = "0218-2130",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "3",

}

TY - JOUR

T1 - Kernel sparse models for automated tumor segmentation

AU - Thiagarajan, Jayaraman J.

AU - Ramamurthy, Karthikeyan Natesan

AU - Rajan, Deepta

AU - Spanias, Andreas

AU - Puri, Anup

AU - Frakes, David

PY - 2014

Y1 - 2014

N2 - In this paper, we propose sparse coding-based approaches for segmentation of tumor regions from magnetic resonance (MR) images. Sparse coding with data-adapted dictionaries has been successfully employed in several image recovery and vision problems. The proposed approaches obtain sparse codes for each pixel in brain MR images considering their intensity values and location information. Since it is trivial to obtain pixel-wise sparse codes, and combining multiple features in the sparse coding setup is not straight-forward, we propose to perform sparse coding in a high-dimensional feature space where non-linear similarities can be effectively modeled. We use the training data from expert-segmented images to obtain kernel dictionaries with the kernel K-lines clustering procedure. For a test image, sparse codes are computed with these kernel dictionaries, and they are used to identify the tumor regions. This approach is completely automated, and does not require user intervention to initialize the tumor regions in a test image. Furthermore, a low complexity segmentation approach based on kernel sparse codes, which allows the user to initialize the tumor region, is also presented. Results obtained with both the proposed approaches are validated against manual segmentation by an expert radiologist, and it is shown that proposed methods lead to accurate tumor identification.

AB - In this paper, we propose sparse coding-based approaches for segmentation of tumor regions from magnetic resonance (MR) images. Sparse coding with data-adapted dictionaries has been successfully employed in several image recovery and vision problems. The proposed approaches obtain sparse codes for each pixel in brain MR images considering their intensity values and location information. Since it is trivial to obtain pixel-wise sparse codes, and combining multiple features in the sparse coding setup is not straight-forward, we propose to perform sparse coding in a high-dimensional feature space where non-linear similarities can be effectively modeled. We use the training data from expert-segmented images to obtain kernel dictionaries with the kernel K-lines clustering procedure. For a test image, sparse codes are computed with these kernel dictionaries, and they are used to identify the tumor regions. This approach is completely automated, and does not require user intervention to initialize the tumor regions in a test image. Furthermore, a low complexity segmentation approach based on kernel sparse codes, which allows the user to initialize the tumor region, is also presented. Results obtained with both the proposed approaches are validated against manual segmentation by an expert radiologist, and it is shown that proposed methods lead to accurate tumor identification.

KW - dictionary learning

KW - kernel methods

KW - MRI

KW - sparse representations

KW - tumor segmentation

UR - http://www.scopus.com/inward/record.url?scp=84906877095&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906877095&partnerID=8YFLogxK

U2 - 10.1142/S0218213014600045

DO - 10.1142/S0218213014600045

M3 - Article

AN - SCOPUS:84906877095

VL - 23

JO - International Journal on Artificial Intelligence Tools

JF - International Journal on Artificial Intelligence Tools

SN - 0218-2130

IS - 3

M1 - 1460004

ER -