Longitudinal intensity normalization in the presence of multiple sclerosis lesions

Snehashis Roy, Aaron Carass, Navid Shiee, Dzung L. Pham, Peter Calabresi, Daniel Reich, Jerry Ladd Prince

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

Abstract

This paper proposes a longitudinal intensity normalization algorithm for T1-weighted magnetic resonance images of human brains in the presence of multiple sclerosis lesions, aiming towards stable and consistent longitudinal segmentations. Unlike previous longitudinal segmentation methods, we propose a 4D intensity normalization that can be used as a preprocessing step to any segmentation method. The variability in intensities arising from the relapsing and remitting nature of the multiple sclerosis lesions is modeled into an otherwise smooth intensity transform based on first order auto-regressive models, resulting in smooth changes in segmentation statistics of normal tissues, while keeping the lesion information unaffected. We validated our method on both simulated and real longitudinal normal subjects and on multiple sclerosis subjects.

Original languageEnglish (US)
Title of host publicationProceedings - International Symposium on Biomedical Imaging
Pages1384-1387
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
Multiple Sclerosis
Brain
Statistics
Tissue
Relapsing-Remitting Multiple Sclerosis
Magnetic Resonance Spectroscopy

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., Shiee, N., Pham, D. L., Calabresi, P., Reich, D., & Prince, J. L. (2013). Longitudinal intensity normalization in the presence of multiple sclerosis lesions. In Proceedings - International Symposium on Biomedical Imaging (pp. 1384-1387). [6556791] https://doi.org/10.1109/ISBI.2013.6556791

Longitudinal intensity normalization in the presence of multiple sclerosis lesions. / Roy, Snehashis; Carass, Aaron; Shiee, Navid; Pham, Dzung L.; Calabresi, Peter; Reich, Daniel; Prince, Jerry Ladd.

Proceedings - International Symposium on Biomedical Imaging. 2013. p. 1384-1387 6556791.

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

Roy, S, Carass, A, Shiee, N, Pham, DL, Calabresi, P, Reich, D & Prince, JL 2013, Longitudinal intensity normalization in the presence of multiple sclerosis lesions. in Proceedings - International Symposium on Biomedical Imaging., 6556791, pp. 1384-1387, 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.2013.6556791
Roy S, Carass A, Shiee N, Pham DL, Calabresi P, Reich D et al. Longitudinal intensity normalization in the presence of multiple sclerosis lesions. In Proceedings - International Symposium on Biomedical Imaging. 2013. p. 1384-1387. 6556791 https://doi.org/10.1109/ISBI.2013.6556791
Roy, Snehashis ; Carass, Aaron ; Shiee, Navid ; Pham, Dzung L. ; Calabresi, Peter ; Reich, Daniel ; Prince, Jerry Ladd. / Longitudinal intensity normalization in the presence of multiple sclerosis lesions. Proceedings - International Symposium on Biomedical Imaging. 2013. pp. 1384-1387
@inproceedings{5d4574b8b17344a7a339beeadb824b49,
title = "Longitudinal intensity normalization in the presence of multiple sclerosis lesions",
abstract = "This paper proposes a longitudinal intensity normalization algorithm for T1-weighted magnetic resonance images of human brains in the presence of multiple sclerosis lesions, aiming towards stable and consistent longitudinal segmentations. Unlike previous longitudinal segmentation methods, we propose a 4D intensity normalization that can be used as a preprocessing step to any segmentation method. The variability in intensities arising from the relapsing and remitting nature of the multiple sclerosis lesions is modeled into an otherwise smooth intensity transform based on first order auto-regressive models, resulting in smooth changes in segmentation statistics of normal tissues, while keeping the lesion information unaffected. We validated our method on both simulated and real longitudinal normal subjects and on multiple sclerosis subjects.",
keywords = "brain, intensity normalization, intensity standardization, MRI, segmentation",
author = "Snehashis Roy and Aaron Carass and Navid Shiee and Pham, {Dzung L.} and Peter Calabresi and Daniel Reich and Prince, {Jerry Ladd}",
year = "2013",
doi = "10.1109/ISBI.2013.6556791",
language = "English (US)",
isbn = "9781467364546",
pages = "1384--1387",
booktitle = "Proceedings - International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - Longitudinal intensity normalization in the presence of multiple sclerosis lesions

AU - Roy, Snehashis

AU - Carass, Aaron

AU - Shiee, Navid

AU - Pham, Dzung L.

AU - Calabresi, Peter

AU - Reich, Daniel

AU - Prince, Jerry Ladd

PY - 2013

Y1 - 2013

N2 - This paper proposes a longitudinal intensity normalization algorithm for T1-weighted magnetic resonance images of human brains in the presence of multiple sclerosis lesions, aiming towards stable and consistent longitudinal segmentations. Unlike previous longitudinal segmentation methods, we propose a 4D intensity normalization that can be used as a preprocessing step to any segmentation method. The variability in intensities arising from the relapsing and remitting nature of the multiple sclerosis lesions is modeled into an otherwise smooth intensity transform based on first order auto-regressive models, resulting in smooth changes in segmentation statistics of normal tissues, while keeping the lesion information unaffected. We validated our method on both simulated and real longitudinal normal subjects and on multiple sclerosis subjects.

AB - This paper proposes a longitudinal intensity normalization algorithm for T1-weighted magnetic resonance images of human brains in the presence of multiple sclerosis lesions, aiming towards stable and consistent longitudinal segmentations. Unlike previous longitudinal segmentation methods, we propose a 4D intensity normalization that can be used as a preprocessing step to any segmentation method. The variability in intensities arising from the relapsing and remitting nature of the multiple sclerosis lesions is modeled into an otherwise smooth intensity transform based on first order auto-regressive models, resulting in smooth changes in segmentation statistics of normal tissues, while keeping the lesion information unaffected. We validated our method on both simulated and real longitudinal normal subjects and on multiple sclerosis subjects.

KW - brain

KW - intensity normalization

KW - intensity standardization

KW - MRI

KW - segmentation

UR - http://www.scopus.com/inward/record.url?scp=84881629967&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881629967&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2013.6556791

DO - 10.1109/ISBI.2013.6556791

M3 - Conference contribution

SN - 9781467364546

SP - 1384

EP - 1387

BT - Proceedings - International Symposium on Biomedical Imaging

ER -