Automatic extraction of bone boundaries from CT scans using an intelligence-based approach

F. Y. Kwan; K. C. Cheung; I. Gibson

doi:10.1109/ICPR.2000.903578

Automatic extraction of bone boundaries from CT scans using an intelligence-based approach

F. Y. Kwan, K. C. Cheung, I. Gibson

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

2 Citations (Scopus)

Abstract

The objective of extracting bone structure boundaries from computed tomography (CT) data is to serve as input for three-dimensional model reconstruction. Various boundary detection algorithms ¹ for CT images have been developed in the last few decades but very few of them are completely automatic. Also, most of them were not capable of dealing with critical locations such as narrow gaps. A novel intelligence-based approach is proposed for automatic extraction of bone boundaries. This approach involves three major steps - gap detection, fuzzy multilevel thresholding and boundary transform (thinning method). Results of applying the approach to CT images are presented, with a discussion of the potential for clinical application.

Original language	English
Title of host publication	Proceedings 15th International Conference on Pattern Recognition. ICPR-2000
Publisher	IEEE
Pages	437-440
Number of pages	4
Volume	15
Edition	3
ISBN (Print)	0-7695-0750-6
DOIs	https://doi.org/10.1109/ICPR.2000.903578
Publication status	Published - 6 Aug 2002
Externally published	Yes
Event	15th International Conference on Pattern Recognition, ICPR 2000 - Barcelona, Spain Duration: 3 Sept 2000 → 7 Sept 2000 Conference number: 15

Conference

Conference	15th International Conference on Pattern Recognition, ICPR 2000
Abbreviated title	ICPR 2000
Country/Territory	Spain
City	Barcelona
Period	3/09/00 → 7/09/00

Access to Document

10.1109/ICPR.2000.903578

Cite this

@inproceedings{c6b9465437fa41019f697366a22f9861,

title = "Automatic extraction of bone boundaries from CT scans using an intelligence-based approach",

abstract = "The objective of extracting bone structure boundaries from computed tomography (CT) data is to serve as input for three-dimensional model reconstruction. Various boundary detection algorithms 1 for CT images have been developed in the last few decades but very few of them are completely automatic. Also, most of them were not capable of dealing with critical locations such as narrow gaps. A novel intelligence-based approach is proposed for automatic extraction of bone boundaries. This approach involves three major steps - gap detection, fuzzy multilevel thresholding and boundary transform (thinning method). Results of applying the approach to CT images are presented, with a discussion of the potential for clinical application.",

author = "Kwan, {F. Y.} and Cheung, {K. C.} and I. Gibson",

year = "2002",

month = aug,

day = "6",

doi = "10.1109/ICPR.2000.903578",

language = "English",

isbn = "0-7695-0750-6",

volume = "15",

pages = "437--440",

booktitle = "Proceedings 15th International Conference on Pattern Recognition. ICPR-2000",

publisher = "IEEE",

address = "United States",

edition = "3",

note = "15th International Conference on Pattern Recognition, ICPR 2000, ICPR 2000 ; Conference date: 03-09-2000 Through 07-09-2000",

}

Kwan, FY, Cheung, KC & Gibson, I 2002, Automatic extraction of bone boundaries from CT scans using an intelligence-based approach. in Proceedings 15th International Conference on Pattern Recognition. ICPR-2000. 3 edn, vol. 15, IEEE, pp. 437-440, 15th International Conference on Pattern Recognition, ICPR 2000, Barcelona, Spain, 3/09/00. https://doi.org/10.1109/ICPR.2000.903578

TY - GEN

T1 - Automatic extraction of bone boundaries from CT scans using an intelligence-based approach

AU - Kwan, F. Y.

AU - Cheung, K. C.

AU - Gibson, I.

N1 - Conference code: 15

PY - 2002/8/6

Y1 - 2002/8/6

N2 - The objective of extracting bone structure boundaries from computed tomography (CT) data is to serve as input for three-dimensional model reconstruction. Various boundary detection algorithms 1 for CT images have been developed in the last few decades but very few of them are completely automatic. Also, most of them were not capable of dealing with critical locations such as narrow gaps. A novel intelligence-based approach is proposed for automatic extraction of bone boundaries. This approach involves three major steps - gap detection, fuzzy multilevel thresholding and boundary transform (thinning method). Results of applying the approach to CT images are presented, with a discussion of the potential for clinical application.

AB - The objective of extracting bone structure boundaries from computed tomography (CT) data is to serve as input for three-dimensional model reconstruction. Various boundary detection algorithms 1 for CT images have been developed in the last few decades but very few of them are completely automatic. Also, most of them were not capable of dealing with critical locations such as narrow gaps. A novel intelligence-based approach is proposed for automatic extraction of bone boundaries. This approach involves three major steps - gap detection, fuzzy multilevel thresholding and boundary transform (thinning method). Results of applying the approach to CT images are presented, with a discussion of the potential for clinical application.

UR - http://www.scopus.com/inward/record.url?scp=33750896455&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2000.903578

DO - 10.1109/ICPR.2000.903578

M3 - Conference contribution

AN - SCOPUS:33750896455

SN - 0-7695-0750-6

VL - 15

SP - 437

EP - 440

BT - Proceedings 15th International Conference on Pattern Recognition. ICPR-2000

PB - IEEE

T2 - 15th International Conference on Pattern Recognition, ICPR 2000

Y2 - 3 September 2000 through 7 September 2000

ER -

Automatic extraction of bone boundaries from CT scans using an intelligence-based approach

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this