Patch based intensity normalization of brain MR images

Snehashis Roy, Aaron Carass, Jerry Ladd Prince

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

Abstract

Magnetic resonance (MR) imaging (MRI) is widely used to study the structure of human brains. Unlike computed tomography (CT), MR image intensities do not have a tissue specific interpretation. Thus images of the same subject obtained with either the same imaging sequence on different scanners or with differing parameters have widely varying intensity scales. This inconsistency introduces errors in segmentation, and other image processing tasks, thus necessitating image intensity standardization. Compared to previous intensity normalization methods using histogram transformations-which try to find a global one-to-one intensity mapping based on histograms-we propose a patch based generative model for intensity normalization between images acquired under different scanners or different pulse sequence parameters. Our method outperforms histogram based methods when normalizing phantoms simulated with various parameters. Additionally, experiments on real data, acquired under a variety of scanners and acquisition parameters, have more consistent segmentations after our normalization.

Original languageEnglish (US)
Title of host publicationProceedings - International Symposium on Biomedical Imaging
Pages342-345
Number of pages4
DOIs
StatePublished - 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

Magnetic resonance
Magnetic resonance imaging
Standardization
Tomography
Brain
Image processing
Magnetic Resonance Spectroscopy
Tissue
Imaging techniques
Experiments
Magnetic Resonance Imaging

Keywords

  • brain
  • intensity normalization
  • intensity standardization
  • MRI
  • segmentation

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Roy, S., Carass, A., & Prince, J. L. (2013). Patch based intensity normalization of brain MR images. In Proceedings - International Symposium on Biomedical Imaging (pp. 342-345). [6556482] https://doi.org/10.1109/ISBI.2013.6556482

Patch based intensity normalization of brain MR images. / Roy, Snehashis; Carass, Aaron; Prince, Jerry Ladd.

Proceedings - International Symposium on Biomedical Imaging. 2013. p. 342-345 6556482.

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

Roy, S, Carass, A & Prince, JL 2013, Patch based intensity normalization of brain MR images. in Proceedings - International Symposium on Biomedical Imaging., 6556482, pp. 342-345, 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.2013.6556482
Roy S, Carass A, Prince JL. Patch based intensity normalization of brain MR images. In Proceedings - International Symposium on Biomedical Imaging. 2013. p. 342-345. 6556482 https://doi.org/10.1109/ISBI.2013.6556482
Roy, Snehashis ; Carass, Aaron ; Prince, Jerry Ladd. / Patch based intensity normalization of brain MR images. Proceedings - International Symposium on Biomedical Imaging. 2013. pp. 342-345
@inproceedings{ba94c4e8d4da4ed8958627302aaa406e,
title = "Patch based intensity normalization of brain MR images",
abstract = "Magnetic resonance (MR) imaging (MRI) is widely used to study the structure of human brains. Unlike computed tomography (CT), MR image intensities do not have a tissue specific interpretation. Thus images of the same subject obtained with either the same imaging sequence on different scanners or with differing parameters have widely varying intensity scales. This inconsistency introduces errors in segmentation, and other image processing tasks, thus necessitating image intensity standardization. Compared to previous intensity normalization methods using histogram transformations-which try to find a global one-to-one intensity mapping based on histograms-we propose a patch based generative model for intensity normalization between images acquired under different scanners or different pulse sequence parameters. Our method outperforms histogram based methods when normalizing phantoms simulated with various parameters. Additionally, experiments on real data, acquired under a variety of scanners and acquisition parameters, have more consistent segmentations after our normalization.",
keywords = "brain, intensity normalization, intensity standardization, MRI, segmentation",
author = "Snehashis Roy and Aaron Carass and Prince, {Jerry Ladd}",
year = "2013",
doi = "10.1109/ISBI.2013.6556482",
language = "English (US)",
isbn = "9781467364546",
pages = "342--345",
booktitle = "Proceedings - International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - Patch based intensity normalization of brain MR images

AU - Roy, Snehashis

AU - Carass, Aaron

AU - Prince, Jerry Ladd

PY - 2013

Y1 - 2013

N2 - Magnetic resonance (MR) imaging (MRI) is widely used to study the structure of human brains. Unlike computed tomography (CT), MR image intensities do not have a tissue specific interpretation. Thus images of the same subject obtained with either the same imaging sequence on different scanners or with differing parameters have widely varying intensity scales. This inconsistency introduces errors in segmentation, and other image processing tasks, thus necessitating image intensity standardization. Compared to previous intensity normalization methods using histogram transformations-which try to find a global one-to-one intensity mapping based on histograms-we propose a patch based generative model for intensity normalization between images acquired under different scanners or different pulse sequence parameters. Our method outperforms histogram based methods when normalizing phantoms simulated with various parameters. Additionally, experiments on real data, acquired under a variety of scanners and acquisition parameters, have more consistent segmentations after our normalization.

AB - Magnetic resonance (MR) imaging (MRI) is widely used to study the structure of human brains. Unlike computed tomography (CT), MR image intensities do not have a tissue specific interpretation. Thus images of the same subject obtained with either the same imaging sequence on different scanners or with differing parameters have widely varying intensity scales. This inconsistency introduces errors in segmentation, and other image processing tasks, thus necessitating image intensity standardization. Compared to previous intensity normalization methods using histogram transformations-which try to find a global one-to-one intensity mapping based on histograms-we propose a patch based generative model for intensity normalization between images acquired under different scanners or different pulse sequence parameters. Our method outperforms histogram based methods when normalizing phantoms simulated with various parameters. Additionally, experiments on real data, acquired under a variety of scanners and acquisition parameters, have more consistent segmentations after our normalization.

KW - brain

KW - intensity normalization

KW - intensity standardization

KW - MRI

KW - segmentation

UR - http://www.scopus.com/inward/record.url?scp=84881646761&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881646761&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2013.6556482

DO - 10.1109/ISBI.2013.6556482

M3 - Conference contribution

C2 - 24443685

AN - SCOPUS:84881646761

SN - 9781467364546

SP - 342

EP - 345

BT - Proceedings - International Symposium on Biomedical Imaging

ER -