Brain tumor segmentation with symmetric texture and symmetric intensity-based decision forests

Anthony Bianchi, James V. Miller, Ek Tsoon Tan, Albert Montillo

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

18 Citations (Scopus)

Abstract

Accurate automated segmentation of brain tumors in MR images is challenging due to overlapping tissue intensity distributions and amorphous tumor shape. However, a clinically viable solution providing precise quantification of tumor and edema volume would enable better pre-operative planning, treatment monitoring and drug development. Our contributions are threefold. First, we design efficient gradient and LBPTOP based texture features which improve classification accuracy over standard intensity features. Second, we extend our texture and intensity features to symmetric texture and symmetric intensity which further improve the accuracy for all tissue classes. Third, we demonstrate further accuracy enhancement by extending our long range features from 100mm to a full 200mm. We assess our brain segmentation technique on 20 patients in the BraTS 2012 dataset. Impact from each contribution is measured and the combination of all the features is shown to yield state-of-the-art accuracy and speed.

Original languageEnglish (US)
Title of host publicationISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro
Pages748-751
Number of pages4
DOIs
StatePublished - Aug 22 2013
Event2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013 - San Francisco, CA, United States
Duration: Apr 7 2013Apr 11 2013

Other

Other2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013
CountryUnited States
CitySan Francisco, CA
Period4/7/134/11/13

Fingerprint

Drug Monitoring
Tissue Distribution
Tumor Burden
Brain Neoplasms
Tumors
Edema
Brain
Textures
Tissue
Neoplasms
Therapeutics
Planning
Monitoring
Datasets
Forests

Keywords

  • brain tumor
  • decision forest
  • Lesion segmentation
  • MRI
  • symmetry
  • texture

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Bianchi, A., Miller, J. V., Tan, E. T., & Montillo, A. (2013). Brain tumor segmentation with symmetric texture and symmetric intensity-based decision forests. In ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro (pp. 748-751). [6556583] https://doi.org/10.1109/ISBI.2013.6556583

Brain tumor segmentation with symmetric texture and symmetric intensity-based decision forests. / Bianchi, Anthony; Miller, James V.; Tan, Ek Tsoon; Montillo, Albert.

ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro. 2013. p. 748-751 6556583.

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

Bianchi, A, Miller, JV, Tan, ET & Montillo, A 2013, Brain tumor segmentation with symmetric texture and symmetric intensity-based decision forests. in ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro., 6556583, pp. 748-751, 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013, San Francisco, CA, United States, 4/7/13. https://doi.org/10.1109/ISBI.2013.6556583
Bianchi A, Miller JV, Tan ET, Montillo A. Brain tumor segmentation with symmetric texture and symmetric intensity-based decision forests. In ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro. 2013. p. 748-751. 6556583 https://doi.org/10.1109/ISBI.2013.6556583
Bianchi, Anthony ; Miller, James V. ; Tan, Ek Tsoon ; Montillo, Albert. / Brain tumor segmentation with symmetric texture and symmetric intensity-based decision forests. ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro. 2013. pp. 748-751
@inproceedings{dbabb15248c54722b60f3830b178547b,
title = "Brain tumor segmentation with symmetric texture and symmetric intensity-based decision forests",
abstract = "Accurate automated segmentation of brain tumors in MR images is challenging due to overlapping tissue intensity distributions and amorphous tumor shape. However, a clinically viable solution providing precise quantification of tumor and edema volume would enable better pre-operative planning, treatment monitoring and drug development. Our contributions are threefold. First, we design efficient gradient and LBPTOP based texture features which improve classification accuracy over standard intensity features. Second, we extend our texture and intensity features to symmetric texture and symmetric intensity which further improve the accuracy for all tissue classes. Third, we demonstrate further accuracy enhancement by extending our long range features from 100mm to a full 200mm. We assess our brain segmentation technique on 20 patients in the BraTS 2012 dataset. Impact from each contribution is measured and the combination of all the features is shown to yield state-of-the-art accuracy and speed.",
keywords = "brain tumor, decision forest, Lesion segmentation, MRI, symmetry, texture",
author = "Anthony Bianchi and Miller, {James V.} and Tan, {Ek Tsoon} and Albert Montillo",
year = "2013",
month = "8",
day = "22",
doi = "10.1109/ISBI.2013.6556583",
language = "English (US)",
isbn = "9781467364546",
pages = "748--751",
booktitle = "ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - Brain tumor segmentation with symmetric texture and symmetric intensity-based decision forests

AU - Bianchi, Anthony

AU - Miller, James V.

AU - Tan, Ek Tsoon

AU - Montillo, Albert

PY - 2013/8/22

Y1 - 2013/8/22

N2 - Accurate automated segmentation of brain tumors in MR images is challenging due to overlapping tissue intensity distributions and amorphous tumor shape. However, a clinically viable solution providing precise quantification of tumor and edema volume would enable better pre-operative planning, treatment monitoring and drug development. Our contributions are threefold. First, we design efficient gradient and LBPTOP based texture features which improve classification accuracy over standard intensity features. Second, we extend our texture and intensity features to symmetric texture and symmetric intensity which further improve the accuracy for all tissue classes. Third, we demonstrate further accuracy enhancement by extending our long range features from 100mm to a full 200mm. We assess our brain segmentation technique on 20 patients in the BraTS 2012 dataset. Impact from each contribution is measured and the combination of all the features is shown to yield state-of-the-art accuracy and speed.

AB - Accurate automated segmentation of brain tumors in MR images is challenging due to overlapping tissue intensity distributions and amorphous tumor shape. However, a clinically viable solution providing precise quantification of tumor and edema volume would enable better pre-operative planning, treatment monitoring and drug development. Our contributions are threefold. First, we design efficient gradient and LBPTOP based texture features which improve classification accuracy over standard intensity features. Second, we extend our texture and intensity features to symmetric texture and symmetric intensity which further improve the accuracy for all tissue classes. Third, we demonstrate further accuracy enhancement by extending our long range features from 100mm to a full 200mm. We assess our brain segmentation technique on 20 patients in the BraTS 2012 dataset. Impact from each contribution is measured and the combination of all the features is shown to yield state-of-the-art accuracy and speed.

KW - brain tumor

KW - decision forest

KW - Lesion segmentation

KW - MRI

KW - symmetry

KW - texture

UR - http://www.scopus.com/inward/record.url?scp=84881643722&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881643722&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2013.6556583

DO - 10.1109/ISBI.2013.6556583

M3 - Conference contribution

C2 - 25404996

AN - SCOPUS:84881643722

SN - 9781467364546

SP - 748

EP - 751

BT - ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging

ER -