Segmentation of multispectral bladder MR images with inhomogeneity correction for virtual cystoscopy

Lihong Li, Zhengrong Liang, Su Wang, Hongyu Lu, Xinzhou Wei, Mark E. Wagshul, Marlene Zawin, Erica J. Posniak, Christopher S. Lee

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

7 Citations (Scopus)

Abstract

Virtual cystoscopy (VC) is a developing noninvasive, safe, and low-cost technique for bladder cancer screening. Multispectral (T1- and T 2-weighted) magnetic resonance (MR) images provide a better tissue contrast between bladder wall and bladder lumen comparing with computed tomography (CT) images. The intrinsic T1 and T2 contrast of the urine against the bladder wall eliminates the invasive air insufflation procedure which is often used in CT-based VC. We propose a new partial volume (PV) segmentation scheme with inhomogeneity correction to segment multispectral MR images for tumor screening by virtual cystoscopy. The proposed PV segmentation algorithm automatically estimates the bias field and segments tissue mixtures inside each voxel of MR images, thus preserving texture information. Experimental results indicate that the present scheme is promising towards mass screening by virtual cystoscopy means.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume6916
DOIs
StatePublished - 2008
Externally publishedYes
EventMedical Imaging 2008 - Physiology, Function, and Structure from Medical Images - San Diego, CA, United States
Duration: Feb 17 2008Feb 19 2008

Other

OtherMedical Imaging 2008 - Physiology, Function, and Structure from Medical Images
CountryUnited States
CitySan Diego, CA
Period2/17/082/19/08

Fingerprint

Magnetic resonance
Screening
Tomography
Tissue
Tumors
Textures
Air
Costs

Keywords

  • Inhomogeneity correction
  • Multispectral MR images
  • Non-invasive screening
  • Partial volume segmentation
  • Virtual cystoscopy

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Li, L., Liang, Z., Wang, S., Lu, H., Wei, X., Wagshul, M. E., ... Lee, C. S. (2008). Segmentation of multispectral bladder MR images with inhomogeneity correction for virtual cystoscopy. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 6916). [69160U] https://doi.org/10.1117/12.769914

Segmentation of multispectral bladder MR images with inhomogeneity correction for virtual cystoscopy. / Li, Lihong; Liang, Zhengrong; Wang, Su; Lu, Hongyu; Wei, Xinzhou; Wagshul, Mark E.; Zawin, Marlene; Posniak, Erica J.; Lee, Christopher S.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6916 2008. 69160U.

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

Li, L, Liang, Z, Wang, S, Lu, H, Wei, X, Wagshul, ME, Zawin, M, Posniak, EJ & Lee, CS 2008, Segmentation of multispectral bladder MR images with inhomogeneity correction for virtual cystoscopy. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 6916, 69160U, Medical Imaging 2008 - Physiology, Function, and Structure from Medical Images, San Diego, CA, United States, 2/17/08. https://doi.org/10.1117/12.769914
Li L, Liang Z, Wang S, Lu H, Wei X, Wagshul ME et al. Segmentation of multispectral bladder MR images with inhomogeneity correction for virtual cystoscopy. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6916. 2008. 69160U https://doi.org/10.1117/12.769914
Li, Lihong ; Liang, Zhengrong ; Wang, Su ; Lu, Hongyu ; Wei, Xinzhou ; Wagshul, Mark E. ; Zawin, Marlene ; Posniak, Erica J. ; Lee, Christopher S. / Segmentation of multispectral bladder MR images with inhomogeneity correction for virtual cystoscopy. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6916 2008.
@inproceedings{ccd548b9d0c24def93202addb23c6946,
title = "Segmentation of multispectral bladder MR images with inhomogeneity correction for virtual cystoscopy",
abstract = "Virtual cystoscopy (VC) is a developing noninvasive, safe, and low-cost technique for bladder cancer screening. Multispectral (T1- and T 2-weighted) magnetic resonance (MR) images provide a better tissue contrast between bladder wall and bladder lumen comparing with computed tomography (CT) images. The intrinsic T1 and T2 contrast of the urine against the bladder wall eliminates the invasive air insufflation procedure which is often used in CT-based VC. We propose a new partial volume (PV) segmentation scheme with inhomogeneity correction to segment multispectral MR images for tumor screening by virtual cystoscopy. The proposed PV segmentation algorithm automatically estimates the bias field and segments tissue mixtures inside each voxel of MR images, thus preserving texture information. Experimental results indicate that the present scheme is promising towards mass screening by virtual cystoscopy means.",
keywords = "Inhomogeneity correction, Multispectral MR images, Non-invasive screening, Partial volume segmentation, Virtual cystoscopy",
author = "Lihong Li and Zhengrong Liang and Su Wang and Hongyu Lu and Xinzhou Wei and Wagshul, {Mark E.} and Marlene Zawin and Posniak, {Erica J.} and Lee, {Christopher S.}",
year = "2008",
doi = "10.1117/12.769914",
language = "English (US)",
isbn = "9780819471000",
volume = "6916",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Segmentation of multispectral bladder MR images with inhomogeneity correction for virtual cystoscopy

AU - Li, Lihong

AU - Liang, Zhengrong

AU - Wang, Su

AU - Lu, Hongyu

AU - Wei, Xinzhou

AU - Wagshul, Mark E.

AU - Zawin, Marlene

AU - Posniak, Erica J.

AU - Lee, Christopher S.

PY - 2008

Y1 - 2008

N2 - Virtual cystoscopy (VC) is a developing noninvasive, safe, and low-cost technique for bladder cancer screening. Multispectral (T1- and T 2-weighted) magnetic resonance (MR) images provide a better tissue contrast between bladder wall and bladder lumen comparing with computed tomography (CT) images. The intrinsic T1 and T2 contrast of the urine against the bladder wall eliminates the invasive air insufflation procedure which is often used in CT-based VC. We propose a new partial volume (PV) segmentation scheme with inhomogeneity correction to segment multispectral MR images for tumor screening by virtual cystoscopy. The proposed PV segmentation algorithm automatically estimates the bias field and segments tissue mixtures inside each voxel of MR images, thus preserving texture information. Experimental results indicate that the present scheme is promising towards mass screening by virtual cystoscopy means.

AB - Virtual cystoscopy (VC) is a developing noninvasive, safe, and low-cost technique for bladder cancer screening. Multispectral (T1- and T 2-weighted) magnetic resonance (MR) images provide a better tissue contrast between bladder wall and bladder lumen comparing with computed tomography (CT) images. The intrinsic T1 and T2 contrast of the urine against the bladder wall eliminates the invasive air insufflation procedure which is often used in CT-based VC. We propose a new partial volume (PV) segmentation scheme with inhomogeneity correction to segment multispectral MR images for tumor screening by virtual cystoscopy. The proposed PV segmentation algorithm automatically estimates the bias field and segments tissue mixtures inside each voxel of MR images, thus preserving texture information. Experimental results indicate that the present scheme is promising towards mass screening by virtual cystoscopy means.

KW - Inhomogeneity correction

KW - Multispectral MR images

KW - Non-invasive screening

KW - Partial volume segmentation

KW - Virtual cystoscopy

UR - http://www.scopus.com/inward/record.url?scp=44349100257&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44349100257&partnerID=8YFLogxK

U2 - 10.1117/12.769914

DO - 10.1117/12.769914

M3 - Conference contribution

AN - SCOPUS:44349100257

SN - 9780819471000

VL - 6916

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -