Computer vision based hairline mandibular fracture detection from computed tomography images

Ananda S. Chowdhury, Anindita Mukherjee, Suchendra M. Bhandarkar, Jack C. Yu

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

This chapter addresses the problem of detection of hairline mandibular fractures from a sequence of computed tomography (CT) images. It has been observed that such a fracture can be easily overlooked during manual detection due to the absence of sharp surface and contour discontinuities and the presence of intensity inhomogeneity in the CT images. In this work, the 2D CT image slices of a mandible with hairline fractures are first identified from the input sequence of a fractured craniofacial skeleton. Two intensity-based image retrieval schemes with different measures of similarity, namely the Jaccard index and the Kolmogorov-Smirnov distance, are applied for that purpose. In the second part, we detect a hairline fracture in the previously identified subset of images using the maximum flow-minimum cut algorithm. 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 constructed using the geometry of the human mandible. The Ford-Fulkerson algorithm with Edmonds-Karp refinement is employed to obtain a minimum cut. Experimental results demonstrate the effectiveness of the proposed method.

Original languageEnglish (US)
Title of host publicationAdvanced Computational Approaches to Biomedical Engineering
PublisherSpringer-Verlag Berlin Heidelberg
Pages193-212
Number of pages20
Volume9783642415395
ISBN (Electronic)9783642415395
ISBN (Print)3642415385, 9783642415388
DOIs
StatePublished - Jan 1 2014

Fingerprint

Computer vision
Tomography
Image retrieval
Bone
Geometry

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Chowdhury, A. S., Mukherjee, A., Bhandarkar, S. M., & Yu, J. C. (2014). Computer vision based hairline mandibular fracture detection from computed tomography images. In Advanced Computational Approaches to Biomedical Engineering (Vol. 9783642415395, pp. 193-212). Springer-Verlag Berlin Heidelberg. https://doi.org/10.1007/978-3-642-41539-5_9

Computer vision based hairline mandibular fracture detection from computed tomography images. / Chowdhury, Ananda S.; Mukherjee, Anindita; Bhandarkar, Suchendra M.; Yu, Jack C.

Advanced Computational Approaches to Biomedical Engineering. Vol. 9783642415395 Springer-Verlag Berlin Heidelberg, 2014. p. 193-212.

Research output: Chapter in Book/Report/Conference proceedingChapter

Chowdhury, AS, Mukherjee, A, Bhandarkar, SM & Yu, JC 2014, Computer vision based hairline mandibular fracture detection from computed tomography images. in Advanced Computational Approaches to Biomedical Engineering. vol. 9783642415395, Springer-Verlag Berlin Heidelberg, pp. 193-212. https://doi.org/10.1007/978-3-642-41539-5_9
Chowdhury AS, Mukherjee A, Bhandarkar SM, Yu JC. Computer vision based hairline mandibular fracture detection from computed tomography images. In Advanced Computational Approaches to Biomedical Engineering. Vol. 9783642415395. Springer-Verlag Berlin Heidelberg. 2014. p. 193-212 https://doi.org/10.1007/978-3-642-41539-5_9
Chowdhury, Ananda S. ; Mukherjee, Anindita ; Bhandarkar, Suchendra M. ; Yu, Jack C. / Computer vision based hairline mandibular fracture detection from computed tomography images. Advanced Computational Approaches to Biomedical Engineering. Vol. 9783642415395 Springer-Verlag Berlin Heidelberg, 2014. pp. 193-212
@inbook{e99172aa91a849f09ac138569b43ee08,
title = "Computer vision based hairline mandibular fracture detection from computed tomography images",
abstract = "This chapter addresses the problem of detection of hairline mandibular fractures from a sequence of computed tomography (CT) images. It has been observed that such a fracture can be easily overlooked during manual detection due to the absence of sharp surface and contour discontinuities and the presence of intensity inhomogeneity in the CT images. In this work, the 2D CT image slices of a mandible with hairline fractures are first identified from the input sequence of a fractured craniofacial skeleton. Two intensity-based image retrieval schemes with different measures of similarity, namely the Jaccard index and the Kolmogorov-Smirnov distance, are applied for that purpose. In the second part, we detect a hairline fracture in the previously identified subset of images using the maximum flow-minimum cut algorithm. 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 constructed using the geometry of the human mandible. The Ford-Fulkerson algorithm with Edmonds-Karp refinement is employed to obtain a minimum cut. Experimental results demonstrate the effectiveness of the proposed method.",
author = "Chowdhury, {Ananda S.} and Anindita Mukherjee and Bhandarkar, {Suchendra M.} and Yu, {Jack C.}",
year = "2014",
month = "1",
day = "1",
doi = "10.1007/978-3-642-41539-5_9",
language = "English (US)",
isbn = "3642415385",
volume = "9783642415395",
pages = "193--212",
booktitle = "Advanced Computational Approaches to Biomedical Engineering",
publisher = "Springer-Verlag Berlin Heidelberg",

}

TY - CHAP

T1 - Computer vision based hairline mandibular fracture detection from computed tomography images

AU - Chowdhury, Ananda S.

AU - Mukherjee, Anindita

AU - Bhandarkar, Suchendra M.

AU - Yu, Jack C.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - This chapter addresses the problem of detection of hairline mandibular fractures from a sequence of computed tomography (CT) images. It has been observed that such a fracture can be easily overlooked during manual detection due to the absence of sharp surface and contour discontinuities and the presence of intensity inhomogeneity in the CT images. In this work, the 2D CT image slices of a mandible with hairline fractures are first identified from the input sequence of a fractured craniofacial skeleton. Two intensity-based image retrieval schemes with different measures of similarity, namely the Jaccard index and the Kolmogorov-Smirnov distance, are applied for that purpose. In the second part, we detect a hairline fracture in the previously identified subset of images using the maximum flow-minimum cut algorithm. 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 constructed using the geometry of the human mandible. The Ford-Fulkerson algorithm with Edmonds-Karp refinement is employed to obtain a minimum cut. Experimental results demonstrate the effectiveness of the proposed method.

AB - This chapter addresses the problem of detection of hairline mandibular fractures from a sequence of computed tomography (CT) images. It has been observed that such a fracture can be easily overlooked during manual detection due to the absence of sharp surface and contour discontinuities and the presence of intensity inhomogeneity in the CT images. In this work, the 2D CT image slices of a mandible with hairline fractures are first identified from the input sequence of a fractured craniofacial skeleton. Two intensity-based image retrieval schemes with different measures of similarity, namely the Jaccard index and the Kolmogorov-Smirnov distance, are applied for that purpose. In the second part, we detect a hairline fracture in the previously identified subset of images using the maximum flow-minimum cut algorithm. 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 constructed using the geometry of the human mandible. The Ford-Fulkerson algorithm with Edmonds-Karp refinement is employed to obtain a minimum cut. Experimental results demonstrate the effectiveness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=84930333567&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84930333567&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-41539-5_9

DO - 10.1007/978-3-642-41539-5_9

M3 - Chapter

AN - SCOPUS:84930333567

SN - 3642415385

SN - 9783642415388

VL - 9783642415395

SP - 193

EP - 212

BT - Advanced Computational Approaches to Biomedical Engineering

PB - Springer-Verlag Berlin Heidelberg

ER -