### Abstract

Automated detection of stable fracture points in a sequence of Computed Tomography (CT) images is a challenging task. In this paper, an innovative scheme for automatic fracture detection in CT images is presented. The input to the system is a sequence of CT image slices of a fractured human mandible. Techniques based on curvature scale-space theory and graph-based filtering (using prior anatomical knowledge) are used to first detect candidate fracture points in the individual CT slices. Subsequently, a Kalman filter incorporating a Bayesian perspective is employed for testing the consistency of the candidate fracture points across all the CT slices in a given sequence. For the purpose of checking statistical consistency, both 95% and 99% high posterior density (HPD) prediction intervals are constructed. A spatial consistency term is formulated for each candidate fracture point in terms of the number of slices in the CT image sequence, the number of times a fracture point detected in that sequence and the number of times it is found to be statistically consistent. Fracture points with spatial consistency terms close to unity are deemed to be stable fracture points for the CT image sequence under consideration.

Original language | English (US) |
---|---|

Title of host publication | 2006 3rd IEEE International Symposium on Biomedical Imaging |

Subtitle of host publication | From Nano to Macro - Proceedings |

Pages | 1320-1323 |

Number of pages | 4 |

Volume | 2006 |

State | Published - Nov 17 2006 |

Event | 2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Arlington, VA, United States Duration: Apr 6 2006 → Apr 9 2006 |

### Other

Other | 2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro |
---|---|

Country | United States |

City | Arlington, VA |

Period | 4/6/06 → 4/9/06 |

### Fingerprint

### Keywords

- Bayesian statistics
- Computed tomography
- Curvature scale space
- Graph-based filtering
- Kalman filter
- Spatial consistency

### ASJC Scopus subject areas

- Engineering(all)

### Cite this

*2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings*(Vol. 2006, pp. 1320-1323). [1625169]

**Automated detection of stable fracture points in computed tomography image sequences.** / Chowdhuty, A. S.; Bhandarkar, S. M.; Datta, G.; Yu, Jack C.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings.*vol. 2006, 1625169, pp. 1320-1323, 2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Arlington, VA, United States, 4/6/06.

}

TY - GEN

T1 - Automated detection of stable fracture points in computed tomography image sequences

AU - Chowdhuty, A. S.

AU - Bhandarkar, S. M.

AU - Datta, G.

AU - Yu, Jack C

PY - 2006/11/17

Y1 - 2006/11/17

N2 - Automated detection of stable fracture points in a sequence of Computed Tomography (CT) images is a challenging task. In this paper, an innovative scheme for automatic fracture detection in CT images is presented. The input to the system is a sequence of CT image slices of a fractured human mandible. Techniques based on curvature scale-space theory and graph-based filtering (using prior anatomical knowledge) are used to first detect candidate fracture points in the individual CT slices. Subsequently, a Kalman filter incorporating a Bayesian perspective is employed for testing the consistency of the candidate fracture points across all the CT slices in a given sequence. For the purpose of checking statistical consistency, both 95% and 99% high posterior density (HPD) prediction intervals are constructed. A spatial consistency term is formulated for each candidate fracture point in terms of the number of slices in the CT image sequence, the number of times a fracture point detected in that sequence and the number of times it is found to be statistically consistent. Fracture points with spatial consistency terms close to unity are deemed to be stable fracture points for the CT image sequence under consideration.

AB - Automated detection of stable fracture points in a sequence of Computed Tomography (CT) images is a challenging task. In this paper, an innovative scheme for automatic fracture detection in CT images is presented. The input to the system is a sequence of CT image slices of a fractured human mandible. Techniques based on curvature scale-space theory and graph-based filtering (using prior anatomical knowledge) are used to first detect candidate fracture points in the individual CT slices. Subsequently, a Kalman filter incorporating a Bayesian perspective is employed for testing the consistency of the candidate fracture points across all the CT slices in a given sequence. For the purpose of checking statistical consistency, both 95% and 99% high posterior density (HPD) prediction intervals are constructed. A spatial consistency term is formulated for each candidate fracture point in terms of the number of slices in the CT image sequence, the number of times a fracture point detected in that sequence and the number of times it is found to be statistically consistent. Fracture points with spatial consistency terms close to unity are deemed to be stable fracture points for the CT image sequence under consideration.

KW - Bayesian statistics

KW - Computed tomography

KW - Curvature scale space

KW - Graph-based filtering

KW - Kalman filter

KW - Spatial consistency

UR - http://www.scopus.com/inward/record.url?scp=33750952297&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750952297&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33750952297

SN - 0780395778

SN - 9780780395770

VL - 2006

SP - 1320

EP - 1323

BT - 2006 3rd IEEE International Symposium on Biomedical Imaging

ER -