A new partial volume segmentation approach to extract bladder wall for computer aided detection in virtual cystoscopy

Lihong Li, Zigang Wang, Xiang Li, Xinzhou Wei, Howard L. Adler, Wei Huang, Syed Rizvi, Hong Meng, Donald P. Harrington, Zhengrong Liang

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

12 Citations (Scopus)

Abstract

Image Processing and Computer Vision Research Laboratory, Department of Engineering Science and Physics, College of Staten Island, City University of New York, Staten Island, NY 10314 We propose a new partial volume (PV) segmentation scheme to extract bladder wall for computer aided detection (CAD) of bladder lesions using multispectral MR images. Compared with CT images, MR images provide not only a better tissue contrast between bladder wall and bladder lumen, but also the multispectral information. As multispectral images are spatially registered over three-dimensional space, information extracted from them is more valuable than that extracted from each image individually. Furthermore, the intrinsic T 1 and T 2 contrast of the urine against the bladder wall eliminates the invasive air insufflation procedure. Because the earliest stages of bladder lesion growth tend to develop gradually and migrate slowly from the mucosa into the bladder wall, our proposed PV algorithm quantifies images as percentages of tissues inside each voxel. It preserves both morphology and texture information and provides tissue growth tendency in addition to the anatomical structure. Our CAD system utilizes a multi-scan protocol on dual (full and empty of urine) states of the bladder to extract both geometrical and texture information. Moreover, multi-scan of transverse and coronal MR images eliminates motion artifacts. Experimental results indicate that the presented scheme is feasible towards mass screening and lesion detection for virtual cystoscopy (VC).

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsA.A. Amini, A. Mandura
Pages199-206
Number of pages8
Volume5369
DOIs
StatePublished - 2004
Externally publishedYes
EventMedical Imaging 2004: Physiology, Function, and Structure from Medical Images - San Diego, CA, United States
Duration: Feb 15 2004Feb 17 2004

Other

OtherMedical Imaging 2004: Physiology, Function, and Structure from Medical Images
CountryUnited States
CitySan Diego, CA
Period2/15/042/17/04

Fingerprint

bladder
Tissue
Textures
lesions
Research laboratories
Computer vision
urine
Screening
Image processing
Physics
textures
Air
lumens
computer vision
image processing
artifacts
tendencies
screening
engineering
physics

Keywords

  • Computer aided detection
  • Mri-based virtual cystoscopy
  • Non-invasive screening
  • Partial volume segmentation
  • Virtual endoscopy

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Li, L., Wang, Z., Li, X., Wei, X., Adler, H. L., Huang, W., ... Liang, Z. (2004). A new partial volume segmentation approach to extract bladder wall for computer aided detection in virtual cystoscopy. In A. A. Amini, & A. Mandura (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 5369, pp. 199-206) https://doi.org/10.1117/12.535913

A new partial volume segmentation approach to extract bladder wall for computer aided detection in virtual cystoscopy. / Li, Lihong; Wang, Zigang; Li, Xiang; Wei, Xinzhou; Adler, Howard L.; Huang, Wei; Rizvi, Syed; Meng, Hong; Harrington, Donald P.; Liang, Zhengrong.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / A.A. Amini; A. Mandura. Vol. 5369 2004. p. 199-206.

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

Li, L, Wang, Z, Li, X, Wei, X, Adler, HL, Huang, W, Rizvi, S, Meng, H, Harrington, DP & Liang, Z 2004, A new partial volume segmentation approach to extract bladder wall for computer aided detection in virtual cystoscopy. in AA Amini & A Mandura (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 5369, pp. 199-206, Medical Imaging 2004: Physiology, Function, and Structure from Medical Images, San Diego, CA, United States, 2/15/04. https://doi.org/10.1117/12.535913
Li L, Wang Z, Li X, Wei X, Adler HL, Huang W et al. A new partial volume segmentation approach to extract bladder wall for computer aided detection in virtual cystoscopy. In Amini AA, Mandura A, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 5369. 2004. p. 199-206 https://doi.org/10.1117/12.535913
Li, Lihong ; Wang, Zigang ; Li, Xiang ; Wei, Xinzhou ; Adler, Howard L. ; Huang, Wei ; Rizvi, Syed ; Meng, Hong ; Harrington, Donald P. ; Liang, Zhengrong. / A new partial volume segmentation approach to extract bladder wall for computer aided detection in virtual cystoscopy. Proceedings of SPIE - The International Society for Optical Engineering. editor / A.A. Amini ; A. Mandura. Vol. 5369 2004. pp. 199-206
@inproceedings{6e17564dbf42492f8af309268056351b,
title = "A new partial volume segmentation approach to extract bladder wall for computer aided detection in virtual cystoscopy",
abstract = "Image Processing and Computer Vision Research Laboratory, Department of Engineering Science and Physics, College of Staten Island, City University of New York, Staten Island, NY 10314 We propose a new partial volume (PV) segmentation scheme to extract bladder wall for computer aided detection (CAD) of bladder lesions using multispectral MR images. Compared with CT images, MR images provide not only a better tissue contrast between bladder wall and bladder lumen, but also the multispectral information. As multispectral images are spatially registered over three-dimensional space, information extracted from them is more valuable than that extracted from each image individually. Furthermore, the intrinsic T 1 and T 2 contrast of the urine against the bladder wall eliminates the invasive air insufflation procedure. Because the earliest stages of bladder lesion growth tend to develop gradually and migrate slowly from the mucosa into the bladder wall, our proposed PV algorithm quantifies images as percentages of tissues inside each voxel. It preserves both morphology and texture information and provides tissue growth tendency in addition to the anatomical structure. Our CAD system utilizes a multi-scan protocol on dual (full and empty of urine) states of the bladder to extract both geometrical and texture information. Moreover, multi-scan of transverse and coronal MR images eliminates motion artifacts. Experimental results indicate that the presented scheme is feasible towards mass screening and lesion detection for virtual cystoscopy (VC).",
keywords = "Computer aided detection, Mri-based virtual cystoscopy, Non-invasive screening, Partial volume segmentation, Virtual endoscopy",
author = "Lihong Li and Zigang Wang and Xiang Li and Xinzhou Wei and Adler, {Howard L.} and Wei Huang and Syed Rizvi and Hong Meng and Harrington, {Donald P.} and Zhengrong Liang",
year = "2004",
doi = "10.1117/12.535913",
language = "English (US)",
volume = "5369",
pages = "199--206",
editor = "A.A. Amini and A. Mandura",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - A new partial volume segmentation approach to extract bladder wall for computer aided detection in virtual cystoscopy

AU - Li, Lihong

AU - Wang, Zigang

AU - Li, Xiang

AU - Wei, Xinzhou

AU - Adler, Howard L.

AU - Huang, Wei

AU - Rizvi, Syed

AU - Meng, Hong

AU - Harrington, Donald P.

AU - Liang, Zhengrong

PY - 2004

Y1 - 2004

N2 - Image Processing and Computer Vision Research Laboratory, Department of Engineering Science and Physics, College of Staten Island, City University of New York, Staten Island, NY 10314 We propose a new partial volume (PV) segmentation scheme to extract bladder wall for computer aided detection (CAD) of bladder lesions using multispectral MR images. Compared with CT images, MR images provide not only a better tissue contrast between bladder wall and bladder lumen, but also the multispectral information. As multispectral images are spatially registered over three-dimensional space, information extracted from them is more valuable than that extracted from each image individually. Furthermore, the intrinsic T 1 and T 2 contrast of the urine against the bladder wall eliminates the invasive air insufflation procedure. Because the earliest stages of bladder lesion growth tend to develop gradually and migrate slowly from the mucosa into the bladder wall, our proposed PV algorithm quantifies images as percentages of tissues inside each voxel. It preserves both morphology and texture information and provides tissue growth tendency in addition to the anatomical structure. Our CAD system utilizes a multi-scan protocol on dual (full and empty of urine) states of the bladder to extract both geometrical and texture information. Moreover, multi-scan of transverse and coronal MR images eliminates motion artifacts. Experimental results indicate that the presented scheme is feasible towards mass screening and lesion detection for virtual cystoscopy (VC).

AB - Image Processing and Computer Vision Research Laboratory, Department of Engineering Science and Physics, College of Staten Island, City University of New York, Staten Island, NY 10314 We propose a new partial volume (PV) segmentation scheme to extract bladder wall for computer aided detection (CAD) of bladder lesions using multispectral MR images. Compared with CT images, MR images provide not only a better tissue contrast between bladder wall and bladder lumen, but also the multispectral information. As multispectral images are spatially registered over three-dimensional space, information extracted from them is more valuable than that extracted from each image individually. Furthermore, the intrinsic T 1 and T 2 contrast of the urine against the bladder wall eliminates the invasive air insufflation procedure. Because the earliest stages of bladder lesion growth tend to develop gradually and migrate slowly from the mucosa into the bladder wall, our proposed PV algorithm quantifies images as percentages of tissues inside each voxel. It preserves both morphology and texture information and provides tissue growth tendency in addition to the anatomical structure. Our CAD system utilizes a multi-scan protocol on dual (full and empty of urine) states of the bladder to extract both geometrical and texture information. Moreover, multi-scan of transverse and coronal MR images eliminates motion artifacts. Experimental results indicate that the presented scheme is feasible towards mass screening and lesion detection for virtual cystoscopy (VC).

KW - Computer aided detection

KW - Mri-based virtual cystoscopy

KW - Non-invasive screening

KW - Partial volume segmentation

KW - Virtual endoscopy

UR - http://www.scopus.com/inward/record.url?scp=3042690342&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=3042690342&partnerID=8YFLogxK

U2 - 10.1117/12.535913

DO - 10.1117/12.535913

M3 - Conference contribution

VL - 5369

SP - 199

EP - 206

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Amini, A.A.

A2 - Mandura, A.

ER -