Robust colon residue detection using vector quantization based classification for virtual colonoscopy

Sarang Lakare; Dongqing Chen; Lihong Li; Arie Kaufman; Mark Wax; Zhengrong Liang

doi:10.1117/12.480410

Robust colon residue detection using vector quantization based classification for virtual colonoscopy

Sarang Lakare
, Dongqing Chen
, Lihong Li
, Arie Kaufman
, Mark Wax
, Zhengrong Liang

Stony Brook University

Research output: Contribution to journal › Conference article › peer-review

9 Scopus citations

Abstract

We present an automatic and robust tagged-residue detection technique using vector quantization based classification. This technique enables electronic cleansing even on poorly tagged datasets, leading to more effective virtual colonoscopy. In order to reduce the sensitivity towards intensity variation among the tagged residual material, we use a multi-step technique. First, we apply classification using an unsupervised and self-adapting vector quantization algorithm. Then, we sort the resultant classes by their average intensities. We apply thresholding on these classes based on a conservative threshold. This helps us in differentiating soft tissue inside tagged material from poorly tagged region or noise.

Original language	English
Pages (from-to)	515-520
Number of pages	6
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	5031
DOIs	https://doi.org/10.1117/12.480410
State	Published - 2003
Event	Medical Imaging 2003: Physiology and Function: Methods, Systems, and Applications - San Diego, CA, United States Duration: Feb 16 2003 → Feb 18 2003

Keywords

Electronic cleansing
Segmentation
Vector quantization
Virtual colonoscopy

Access to Document

10.1117/12.480410

Cite this

@article{a9685eacd5494883880236671d188273,

title = "Robust colon residue detection using vector quantization based classification for virtual colonoscopy",

abstract = "We present an automatic and robust tagged-residue detection technique using vector quantization based classification. This technique enables electronic cleansing even on poorly tagged datasets, leading to more effective virtual colonoscopy. In order to reduce the sensitivity towards intensity variation among the tagged residual material, we use a multi-step technique. First, we apply classification using an unsupervised and self-adapting vector quantization algorithm. Then, we sort the resultant classes by their average intensities. We apply thresholding on these classes based on a conservative threshold. This helps us in differentiating soft tissue inside tagged material from poorly tagged region or noise.",

keywords = "Electronic cleansing, Segmentation, Vector quantization, Virtual colonoscopy",

author = "Sarang Lakare and Dongqing Chen and Lihong Li and Arie Kaufman and Mark Wax and Zhengrong Liang",

year = "2003",

doi = "10.1117/12.480410",

language = "English",

volume = "5031",

pages = "515--520",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

note = "Medical Imaging 2003: Physiology and Function: Methods, Systems, and Applications ; Conference date: 16-02-2003 Through 18-02-2003",

}

TY - JOUR

T1 - Robust colon residue detection using vector quantization based classification for virtual colonoscopy

AU - Lakare, Sarang

AU - Chen, Dongqing

AU - Li, Lihong

AU - Kaufman, Arie

AU - Wax, Mark

AU - Liang, Zhengrong

PY - 2003

Y1 - 2003

N2 - We present an automatic and robust tagged-residue detection technique using vector quantization based classification. This technique enables electronic cleansing even on poorly tagged datasets, leading to more effective virtual colonoscopy. In order to reduce the sensitivity towards intensity variation among the tagged residual material, we use a multi-step technique. First, we apply classification using an unsupervised and self-adapting vector quantization algorithm. Then, we sort the resultant classes by their average intensities. We apply thresholding on these classes based on a conservative threshold. This helps us in differentiating soft tissue inside tagged material from poorly tagged region or noise.

AB - We present an automatic and robust tagged-residue detection technique using vector quantization based classification. This technique enables electronic cleansing even on poorly tagged datasets, leading to more effective virtual colonoscopy. In order to reduce the sensitivity towards intensity variation among the tagged residual material, we use a multi-step technique. First, we apply classification using an unsupervised and self-adapting vector quantization algorithm. Then, we sort the resultant classes by their average intensities. We apply thresholding on these classes based on a conservative threshold. This helps us in differentiating soft tissue inside tagged material from poorly tagged region or noise.

KW - Electronic cleansing

KW - Segmentation

KW - Vector quantization

KW - Virtual colonoscopy

UR - https://www.scopus.com/pages/publications/0042828865

U2 - 10.1117/12.480410

DO - 10.1117/12.480410

M3 - Conference article

AN - SCOPUS:0042828865

SN - 0277-786X

VL - 5031

SP - 515

EP - 520

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

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

T2 - Medical Imaging 2003: Physiology and Function: Methods, Systems, and Applications

Y2 - 16 February 2003 through 18 February 2003

ER -

Robust colon residue detection using vector quantization based classification for virtual colonoscopy

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this