A two-level approach towards semantic colon segmentation

removing extra-colonic findings.

L. Lu, Matthias Wolf, Jianming Liang, Murat Dundar, Jinbo Bi, Marcos Salganicoff

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Computer aided detection (CAD) of colonic polyps in computed tomographic colonography has tremendously impacted colorectal cancer diagnosis using 3D medical imaging. It is a prerequisite for all CAD systems to extract the air-distended colon segments from 3D abdomen computed tomography scans. In this paper, we present a two-level statistical approach of first separating colon segments from small intestine, stomach and other extra-colonic parts by classification on a new geometric feature set; then evaluating the overall performance confidence using distance and geometry statistics over patients. The proposed method is fully automatic and validated using both the classification results in the first level and its numerical impacts on false positive reduction of extra-colonic findings in a CAD system. It shows superior performance than the state-of-art knowledge or anatomy based colon segmentation algorithms.

Original languageEnglish (US)
Title of host publicationMedical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Pages1009-1016
Number of pages8
Volume12
EditionPt 2
StatePublished - 2009

Fingerprint

Semantics
Colon
Computed Tomographic Colonography
Colonic Polyps
Diagnostic Imaging
Abdomen
Small Intestine
Colorectal Neoplasms
Anatomy
Stomach
Air
Tomography

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Lu, L., Wolf, M., Liang, J., Dundar, M., Bi, J., & Salganicoff, M. (2009). A two-level approach towards semantic colon segmentation: removing extra-colonic findings. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention (Pt 2 ed., Vol. 12, pp. 1009-1016)

A two-level approach towards semantic colon segmentation : removing extra-colonic findings. / Lu, L.; Wolf, Matthias; Liang, Jianming; Dundar, Murat; Bi, Jinbo; Salganicoff, Marcos.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 12 Pt 2. ed. 2009. p. 1009-1016.

Research output: Chapter in Book/Report/Conference proceedingChapter

Lu, L, Wolf, M, Liang, J, Dundar, M, Bi, J & Salganicoff, M 2009, A two-level approach towards semantic colon segmentation: removing extra-colonic findings. in Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Pt 2 edn, vol. 12, pp. 1009-1016.
Lu L, Wolf M, Liang J, Dundar M, Bi J, Salganicoff M. A two-level approach towards semantic colon segmentation: removing extra-colonic findings. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Pt 2 ed. Vol. 12. 2009. p. 1009-1016
Lu, L. ; Wolf, Matthias ; Liang, Jianming ; Dundar, Murat ; Bi, Jinbo ; Salganicoff, Marcos. / A two-level approach towards semantic colon segmentation : removing extra-colonic findings. Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 12 Pt 2. ed. 2009. pp. 1009-1016
@inbook{2bac2e7ca5784ed9acb18038b8e2f1a3,
title = "A two-level approach towards semantic colon segmentation: removing extra-colonic findings.",
abstract = "Computer aided detection (CAD) of colonic polyps in computed tomographic colonography has tremendously impacted colorectal cancer diagnosis using 3D medical imaging. It is a prerequisite for all CAD systems to extract the air-distended colon segments from 3D abdomen computed tomography scans. In this paper, we present a two-level statistical approach of first separating colon segments from small intestine, stomach and other extra-colonic parts by classification on a new geometric feature set; then evaluating the overall performance confidence using distance and geometry statistics over patients. The proposed method is fully automatic and validated using both the classification results in the first level and its numerical impacts on false positive reduction of extra-colonic findings in a CAD system. It shows superior performance than the state-of-art knowledge or anatomy based colon segmentation algorithms.",
author = "L. Lu and Matthias Wolf and Jianming Liang and Murat Dundar and Jinbo Bi and Marcos Salganicoff",
year = "2009",
language = "English (US)",
volume = "12",
pages = "1009--1016",
booktitle = "Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention",
edition = "Pt 2",

}

TY - CHAP

T1 - A two-level approach towards semantic colon segmentation

T2 - removing extra-colonic findings.

AU - Lu, L.

AU - Wolf, Matthias

AU - Liang, Jianming

AU - Dundar, Murat

AU - Bi, Jinbo

AU - Salganicoff, Marcos

PY - 2009

Y1 - 2009

N2 - Computer aided detection (CAD) of colonic polyps in computed tomographic colonography has tremendously impacted colorectal cancer diagnosis using 3D medical imaging. It is a prerequisite for all CAD systems to extract the air-distended colon segments from 3D abdomen computed tomography scans. In this paper, we present a two-level statistical approach of first separating colon segments from small intestine, stomach and other extra-colonic parts by classification on a new geometric feature set; then evaluating the overall performance confidence using distance and geometry statistics over patients. The proposed method is fully automatic and validated using both the classification results in the first level and its numerical impacts on false positive reduction of extra-colonic findings in a CAD system. It shows superior performance than the state-of-art knowledge or anatomy based colon segmentation algorithms.

AB - Computer aided detection (CAD) of colonic polyps in computed tomographic colonography has tremendously impacted colorectal cancer diagnosis using 3D medical imaging. It is a prerequisite for all CAD systems to extract the air-distended colon segments from 3D abdomen computed tomography scans. In this paper, we present a two-level statistical approach of first separating colon segments from small intestine, stomach and other extra-colonic parts by classification on a new geometric feature set; then evaluating the overall performance confidence using distance and geometry statistics over patients. The proposed method is fully automatic and validated using both the classification results in the first level and its numerical impacts on false positive reduction of extra-colonic findings in a CAD system. It shows superior performance than the state-of-art knowledge or anatomy based colon segmentation algorithms.

UR - http://www.scopus.com/inward/record.url?scp=84855787108&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84855787108&partnerID=8YFLogxK

M3 - Chapter

VL - 12

SP - 1009

EP - 1016

BT - Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention

ER -