Automated labeling of neuroanatomical structures in routine brain CT

Furen Xiao, Chun Chih Liao, I-Jen Chiang, Jau Min Wong

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

Abstract

Although the advance in image technology is remarkable, most routine brain images are still presented in series of sections. We present a technique for automatically assigning neuroanatomical labels to each pixel in brain CT sets based on electronic atlases. In contrast to existing segmentation procedures that focused on thin-cut MRI, our technique could be applied on routine CT images. The technique employs an affine registration for matching skulls to generate template for each slice. A deformable registration procedure is then applied to label the neuroanatomical structures. The performance of our algorithm was evaluated as area overlapping, measured at the lenticular nuclei. The average area overlapping of images without space occupying lesions was 72.3%. With small space occupying lesions, this value is 59.1%. The technique is shown to be of acceptable accuracy for images without space occupying lesions. It might provide basis for computer-assisted diagnosis and report generation system.

Original languageEnglish
Title of host publicationConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Pages3453-3457
Number of pages5
Volume4
DOIs
Publication statusPublished - 2007
Event2006 IEEE International Conference on Systems, Man and Cybernetics - Taipei, Taiwan
Duration: Oct 8 2006Oct 11 2006

Other

Other2006 IEEE International Conference on Systems, Man and Cybernetics
CountryTaiwan
CityTaipei
Period10/8/0610/11/06

Fingerprint

Labeling
Labels
Brain
Magnetic resonance imaging
Pixels

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Xiao, F., Liao, C. C., Chiang, I-J., & Wong, J. M. (2007). Automated labeling of neuroanatomical structures in routine brain CT. In Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics (Vol. 4, pp. 3453-3457). [4274417] https://doi.org/10.1109/ICSMC.2006.384653

Automated labeling of neuroanatomical structures in routine brain CT. / Xiao, Furen; Liao, Chun Chih; Chiang, I-Jen; Wong, Jau Min.

Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. Vol. 4 2007. p. 3453-3457 4274417.

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

Xiao, F, Liao, CC, Chiang, I-J & Wong, JM 2007, Automated labeling of neuroanatomical structures in routine brain CT. in Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. vol. 4, 4274417, pp. 3453-3457, 2006 IEEE International Conference on Systems, Man and Cybernetics, Taipei, Taiwan, 10/8/06. https://doi.org/10.1109/ICSMC.2006.384653
Xiao F, Liao CC, Chiang I-J, Wong JM. Automated labeling of neuroanatomical structures in routine brain CT. In Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. Vol. 4. 2007. p. 3453-3457. 4274417 https://doi.org/10.1109/ICSMC.2006.384653
Xiao, Furen ; Liao, Chun Chih ; Chiang, I-Jen ; Wong, Jau Min. / Automated labeling of neuroanatomical structures in routine brain CT. Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. Vol. 4 2007. pp. 3453-3457
@inproceedings{962d751dd2354b3fb337434fcef18152,
title = "Automated labeling of neuroanatomical structures in routine brain CT",
abstract = "Although the advance in image technology is remarkable, most routine brain images are still presented in series of sections. We present a technique for automatically assigning neuroanatomical labels to each pixel in brain CT sets based on electronic atlases. In contrast to existing segmentation procedures that focused on thin-cut MRI, our technique could be applied on routine CT images. The technique employs an affine registration for matching skulls to generate template for each slice. A deformable registration procedure is then applied to label the neuroanatomical structures. The performance of our algorithm was evaluated as area overlapping, measured at the lenticular nuclei. The average area overlapping of images without space occupying lesions was 72.3{\%}. With small space occupying lesions, this value is 59.1{\%}. The technique is shown to be of acceptable accuracy for images without space occupying lesions. It might provide basis for computer-assisted diagnosis and report generation system.",
author = "Furen Xiao and Liao, {Chun Chih} and I-Jen Chiang and Wong, {Jau Min}",
year = "2007",
doi = "10.1109/ICSMC.2006.384653",
language = "English",
isbn = "1424401003",
volume = "4",
pages = "3453--3457",
booktitle = "Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics",

}

TY - GEN

T1 - Automated labeling of neuroanatomical structures in routine brain CT

AU - Xiao, Furen

AU - Liao, Chun Chih

AU - Chiang, I-Jen

AU - Wong, Jau Min

PY - 2007

Y1 - 2007

N2 - Although the advance in image technology is remarkable, most routine brain images are still presented in series of sections. We present a technique for automatically assigning neuroanatomical labels to each pixel in brain CT sets based on electronic atlases. In contrast to existing segmentation procedures that focused on thin-cut MRI, our technique could be applied on routine CT images. The technique employs an affine registration for matching skulls to generate template for each slice. A deformable registration procedure is then applied to label the neuroanatomical structures. The performance of our algorithm was evaluated as area overlapping, measured at the lenticular nuclei. The average area overlapping of images without space occupying lesions was 72.3%. With small space occupying lesions, this value is 59.1%. The technique is shown to be of acceptable accuracy for images without space occupying lesions. It might provide basis for computer-assisted diagnosis and report generation system.

AB - Although the advance in image technology is remarkable, most routine brain images are still presented in series of sections. We present a technique for automatically assigning neuroanatomical labels to each pixel in brain CT sets based on electronic atlases. In contrast to existing segmentation procedures that focused on thin-cut MRI, our technique could be applied on routine CT images. The technique employs an affine registration for matching skulls to generate template for each slice. A deformable registration procedure is then applied to label the neuroanatomical structures. The performance of our algorithm was evaluated as area overlapping, measured at the lenticular nuclei. The average area overlapping of images without space occupying lesions was 72.3%. With small space occupying lesions, this value is 59.1%. The technique is shown to be of acceptable accuracy for images without space occupying lesions. It might provide basis for computer-assisted diagnosis and report generation system.

UR - http://www.scopus.com/inward/record.url?scp=34548128832&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548128832&partnerID=8YFLogxK

U2 - 10.1109/ICSMC.2006.384653

DO - 10.1109/ICSMC.2006.384653

M3 - Conference contribution

AN - SCOPUS:34548128832

SN - 1424401003

SN - 9781424401000

VL - 4

SP - 3453

EP - 3457

BT - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

ER -