2 Citations (Scopus)

Abstract

Cross section area (CSA) of spinal canal has been an important indicator for lumbar spinal stenosis (LSS), which remains the leading preoperative diagnosis for adults older than 65 years. Due to its irregularity in spatial shape and lack of spectral information, it is a challenging issue to utilize machine learning algorithms to classify this region accurately. Recently, two studies [1,2] shed some light on this topic by considering its spectral information jointly with spatial one as features and evaluated the performance of three popular machine learning algorithms for classification and measurement of CSA. Their experimental studies indicated that it is feasible to classify the CSA region based on its spectral and spatial information. However, the accuracy heavily relies on decent training samples picked from a region which could only be provided from manual marks of experienced doctors. This manuscript aimed to propose an automatic method to remove requirement of human intervention to determine the training region, and further make the supervised classification methods proposed in [1,2] become unsupervised classification methods. The utility and robustness of the proposed method would be demonstrated by the figures and statistical chart presented in the experimental section.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013
Pages3784-3789
Number of pages6
DOIs
Publication statusPublished - 2013
Event2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013 - Manchester, United Kingdom
Duration: Oct 13 2013Oct 16 2013

Other

Other2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013
CountryUnited Kingdom
CityManchester
Period10/13/1310/16/13

Fingerprint

Canals
Learning algorithms
Learning systems

Keywords

  • Cerebrospinal fluid
  • Lumbar spinal stenosis
  • Spinal nerve roots
  • Support vector machine
  • Training region
  • Unsupervised classification

ASJC Scopus subject areas

  • Human-Computer Interaction

Cite this

Wu, C. C., Huang, G. S., Chen, Y. L., Chiang, Y. H., & Lin, J. (2013). Unsupervised classification of cross-section area of spinal canal. In Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013 (pp. 3784-3789). [6722399] https://doi.org/10.1109/SMC.2013.646

Unsupervised classification of cross-section area of spinal canal. / Wu, Chao Cheng; Huang, Guan Sheng; Chen, Yi Ling; Chiang, Yung Hsiao; Lin, Jiannher.

Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013. 2013. p. 3784-3789 6722399.

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

Wu, CC, Huang, GS, Chen, YL, Chiang, YH & Lin, J 2013, Unsupervised classification of cross-section area of spinal canal. in Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013., 6722399, pp. 3784-3789, 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013, Manchester, United Kingdom, 10/13/13. https://doi.org/10.1109/SMC.2013.646
Wu CC, Huang GS, Chen YL, Chiang YH, Lin J. Unsupervised classification of cross-section area of spinal canal. In Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013. 2013. p. 3784-3789. 6722399 https://doi.org/10.1109/SMC.2013.646
Wu, Chao Cheng ; Huang, Guan Sheng ; Chen, Yi Ling ; Chiang, Yung Hsiao ; Lin, Jiannher. / Unsupervised classification of cross-section area of spinal canal. Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013. 2013. pp. 3784-3789
@inproceedings{ad5a11588dec4784bcdbbdadca37b307,
title = "Unsupervised classification of cross-section area of spinal canal",
abstract = "Cross section area (CSA) of spinal canal has been an important indicator for lumbar spinal stenosis (LSS), which remains the leading preoperative diagnosis for adults older than 65 years. Due to its irregularity in spatial shape and lack of spectral information, it is a challenging issue to utilize machine learning algorithms to classify this region accurately. Recently, two studies [1,2] shed some light on this topic by considering its spectral information jointly with spatial one as features and evaluated the performance of three popular machine learning algorithms for classification and measurement of CSA. Their experimental studies indicated that it is feasible to classify the CSA region based on its spectral and spatial information. However, the accuracy heavily relies on decent training samples picked from a region which could only be provided from manual marks of experienced doctors. This manuscript aimed to propose an automatic method to remove requirement of human intervention to determine the training region, and further make the supervised classification methods proposed in [1,2] become unsupervised classification methods. The utility and robustness of the proposed method would be demonstrated by the figures and statistical chart presented in the experimental section.",
keywords = "Cerebrospinal fluid, Lumbar spinal stenosis, Spinal nerve roots, Support vector machine, Training region, Unsupervised classification",
author = "Wu, {Chao Cheng} and Huang, {Guan Sheng} and Chen, {Yi Ling} and Chiang, {Yung Hsiao} and Jiannher Lin",
year = "2013",
doi = "10.1109/SMC.2013.646",
language = "English",
isbn = "9780769551548",
pages = "3784--3789",
booktitle = "Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013",

}

TY - GEN

T1 - Unsupervised classification of cross-section area of spinal canal

AU - Wu, Chao Cheng

AU - Huang, Guan Sheng

AU - Chen, Yi Ling

AU - Chiang, Yung Hsiao

AU - Lin, Jiannher

PY - 2013

Y1 - 2013

N2 - Cross section area (CSA) of spinal canal has been an important indicator for lumbar spinal stenosis (LSS), which remains the leading preoperative diagnosis for adults older than 65 years. Due to its irregularity in spatial shape and lack of spectral information, it is a challenging issue to utilize machine learning algorithms to classify this region accurately. Recently, two studies [1,2] shed some light on this topic by considering its spectral information jointly with spatial one as features and evaluated the performance of three popular machine learning algorithms for classification and measurement of CSA. Their experimental studies indicated that it is feasible to classify the CSA region based on its spectral and spatial information. However, the accuracy heavily relies on decent training samples picked from a region which could only be provided from manual marks of experienced doctors. This manuscript aimed to propose an automatic method to remove requirement of human intervention to determine the training region, and further make the supervised classification methods proposed in [1,2] become unsupervised classification methods. The utility and robustness of the proposed method would be demonstrated by the figures and statistical chart presented in the experimental section.

AB - Cross section area (CSA) of spinal canal has been an important indicator for lumbar spinal stenosis (LSS), which remains the leading preoperative diagnosis for adults older than 65 years. Due to its irregularity in spatial shape and lack of spectral information, it is a challenging issue to utilize machine learning algorithms to classify this region accurately. Recently, two studies [1,2] shed some light on this topic by considering its spectral information jointly with spatial one as features and evaluated the performance of three popular machine learning algorithms for classification and measurement of CSA. Their experimental studies indicated that it is feasible to classify the CSA region based on its spectral and spatial information. However, the accuracy heavily relies on decent training samples picked from a region which could only be provided from manual marks of experienced doctors. This manuscript aimed to propose an automatic method to remove requirement of human intervention to determine the training region, and further make the supervised classification methods proposed in [1,2] become unsupervised classification methods. The utility and robustness of the proposed method would be demonstrated by the figures and statistical chart presented in the experimental section.

KW - Cerebrospinal fluid

KW - Lumbar spinal stenosis

KW - Spinal nerve roots

KW - Support vector machine

KW - Training region

KW - Unsupervised classification

UR - http://www.scopus.com/inward/record.url?scp=84893553281&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893553281&partnerID=8YFLogxK

U2 - 10.1109/SMC.2013.646

DO - 10.1109/SMC.2013.646

M3 - Conference contribution

SN - 9780769551548

SP - 3784

EP - 3789

BT - Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013

ER -