Detection of hairline mandibular fracture using max-flow min-cut and Kolmogorov-Smirnov distance

Ananda S. Chowdhury, Suchendra M. Bhandarkar, Robert W. Robinson, Jack C Yu, Tianming Liu

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

2 Citations (Scopus)

Abstract

This paper addresses the clinically challenging problem of hairline mandibular fracture detection from a sequence of Computed Tomography (CT) images. A hairline fracture of critical clinical importance, can be easily missed due to the absence of sharp surface and contour discontinuities and the presence of intensity inhomogeneity in the CT image, if not scrutinized carefully. In this work, the 2D CT image slices displaying a mandible with hairline fractures are first identified within an input CT image sequence of a fractured craniofacial skeleton. This is achieved via an intensity-based image retrieval scheme using Kolmogorov-Smirnov distance as the measure of similarity and an unbroken mandible as the reference image. Since a hairline fracture is essentially a discontinuity in the bone contour, we model it as a minimum cut in an appropriately weighted flow network. The existing graph cut-based segmentation schemes are enhanced with a novel construction of the flow network, guided by the geometry of the human mandible. The Edmonds-Karp refinement of the classical Ford-Fulkerson algorithm is employed next to obtain a minimum cut, which represents the hairline fracture in the already identified CT image slices. Experimental results demonstrate the effectiveness of the proposed method.

Original languageEnglish (US)
Title of host publication2011 8th IEEE International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro, ISBI'11
Pages1962-1965
Number of pages4
DOIs
StatePublished - Nov 2 2011
Event2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 - Chicago, IL, United States
Duration: Mar 30 2011Apr 2 2011

Other

Other2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11
CountryUnited States
CityChicago, IL
Period3/30/114/2/11

Fingerprint

Mandibular Fractures
Tomography
Mandible
Image retrieval
Skeleton
Bone
Bone and Bones
Geometry

Keywords

  • Hairline mandibular fracture
  • Kolmogorov-Smirnov distance
  • Max-flow mincut

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Chowdhury, A. S., Bhandarkar, S. M., Robinson, R. W., Yu, J. C., & Liu, T. (2011). Detection of hairline mandibular fracture using max-flow min-cut and Kolmogorov-Smirnov distance. In 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 (pp. 1962-1965). [5872794] https://doi.org/10.1109/ISBI.2011.5872794

Detection of hairline mandibular fracture using max-flow min-cut and Kolmogorov-Smirnov distance. / Chowdhury, Ananda S.; Bhandarkar, Suchendra M.; Robinson, Robert W.; Yu, Jack C; Liu, Tianming.

2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11. 2011. p. 1962-1965 5872794.

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

Chowdhury, AS, Bhandarkar, SM, Robinson, RW, Yu, JC & Liu, T 2011, Detection of hairline mandibular fracture using max-flow min-cut and Kolmogorov-Smirnov distance. in 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11., 5872794, pp. 1962-1965, 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11, Chicago, IL, United States, 3/30/11. https://doi.org/10.1109/ISBI.2011.5872794
Chowdhury AS, Bhandarkar SM, Robinson RW, Yu JC, Liu T. Detection of hairline mandibular fracture using max-flow min-cut and Kolmogorov-Smirnov distance. In 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11. 2011. p. 1962-1965. 5872794 https://doi.org/10.1109/ISBI.2011.5872794
Chowdhury, Ananda S. ; Bhandarkar, Suchendra M. ; Robinson, Robert W. ; Yu, Jack C ; Liu, Tianming. / Detection of hairline mandibular fracture using max-flow min-cut and Kolmogorov-Smirnov distance. 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11. 2011. pp. 1962-1965
@inproceedings{e3d122898f53431e9ce5e36d611f53a6,
title = "Detection of hairline mandibular fracture using max-flow min-cut and Kolmogorov-Smirnov distance",
abstract = "This paper addresses the clinically challenging problem of hairline mandibular fracture detection from a sequence of Computed Tomography (CT) images. A hairline fracture of critical clinical importance, can be easily missed due to the absence of sharp surface and contour discontinuities and the presence of intensity inhomogeneity in the CT image, if not scrutinized carefully. In this work, the 2D CT image slices displaying a mandible with hairline fractures are first identified within an input CT image sequence of a fractured craniofacial skeleton. This is achieved via an intensity-based image retrieval scheme using Kolmogorov-Smirnov distance as the measure of similarity and an unbroken mandible as the reference image. Since a hairline fracture is essentially a discontinuity in the bone contour, we model it as a minimum cut in an appropriately weighted flow network. The existing graph cut-based segmentation schemes are enhanced with a novel construction of the flow network, guided by the geometry of the human mandible. The Edmonds-Karp refinement of the classical Ford-Fulkerson algorithm is employed next to obtain a minimum cut, which represents the hairline fracture in the already identified CT image slices. Experimental results demonstrate the effectiveness of the proposed method.",
keywords = "Hairline mandibular fracture, Kolmogorov-Smirnov distance, Max-flow mincut",
author = "Chowdhury, {Ananda S.} and Bhandarkar, {Suchendra M.} and Robinson, {Robert W.} and Yu, {Jack C} and Tianming Liu",
year = "2011",
month = "11",
day = "2",
doi = "10.1109/ISBI.2011.5872794",
language = "English (US)",
isbn = "9781424441280",
pages = "1962--1965",
booktitle = "2011 8th IEEE International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - Detection of hairline mandibular fracture using max-flow min-cut and Kolmogorov-Smirnov distance

AU - Chowdhury, Ananda S.

AU - Bhandarkar, Suchendra M.

AU - Robinson, Robert W.

AU - Yu, Jack C

AU - Liu, Tianming

PY - 2011/11/2

Y1 - 2011/11/2

N2 - This paper addresses the clinically challenging problem of hairline mandibular fracture detection from a sequence of Computed Tomography (CT) images. A hairline fracture of critical clinical importance, can be easily missed due to the absence of sharp surface and contour discontinuities and the presence of intensity inhomogeneity in the CT image, if not scrutinized carefully. In this work, the 2D CT image slices displaying a mandible with hairline fractures are first identified within an input CT image sequence of a fractured craniofacial skeleton. This is achieved via an intensity-based image retrieval scheme using Kolmogorov-Smirnov distance as the measure of similarity and an unbroken mandible as the reference image. Since a hairline fracture is essentially a discontinuity in the bone contour, we model it as a minimum cut in an appropriately weighted flow network. The existing graph cut-based segmentation schemes are enhanced with a novel construction of the flow network, guided by the geometry of the human mandible. The Edmonds-Karp refinement of the classical Ford-Fulkerson algorithm is employed next to obtain a minimum cut, which represents the hairline fracture in the already identified CT image slices. Experimental results demonstrate the effectiveness of the proposed method.

AB - This paper addresses the clinically challenging problem of hairline mandibular fracture detection from a sequence of Computed Tomography (CT) images. A hairline fracture of critical clinical importance, can be easily missed due to the absence of sharp surface and contour discontinuities and the presence of intensity inhomogeneity in the CT image, if not scrutinized carefully. In this work, the 2D CT image slices displaying a mandible with hairline fractures are first identified within an input CT image sequence of a fractured craniofacial skeleton. This is achieved via an intensity-based image retrieval scheme using Kolmogorov-Smirnov distance as the measure of similarity and an unbroken mandible as the reference image. Since a hairline fracture is essentially a discontinuity in the bone contour, we model it as a minimum cut in an appropriately weighted flow network. The existing graph cut-based segmentation schemes are enhanced with a novel construction of the flow network, guided by the geometry of the human mandible. The Edmonds-Karp refinement of the classical Ford-Fulkerson algorithm is employed next to obtain a minimum cut, which represents the hairline fracture in the already identified CT image slices. Experimental results demonstrate the effectiveness of the proposed method.

KW - Hairline mandibular fracture

KW - Kolmogorov-Smirnov distance

KW - Max-flow mincut

UR - http://www.scopus.com/inward/record.url?scp=80055062108&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80055062108&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2011.5872794

DO - 10.1109/ISBI.2011.5872794

M3 - Conference contribution

SN - 9781424441280

SP - 1962

EP - 1965

BT - 2011 8th IEEE International Symposium on Biomedical Imaging

ER -