Unsupervised Classification of Cerebrospinal Fluid by Statistical Indicators

Kuan Ru Lee, Yi Xian Yeh, Chao Cheng Wu, Jiannher Lin, Yung Hsiao Chiang

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

Abstract

Cross section area (CSA) of spinal canal has been a crucial indicator for lumbar spinal stenosis (LSS), which remains the leading preoperative diagnosis for elder people. Recently, the machine learning algorithms have been investigated in[7-10] for automatic classification systems. The methods investigated in[7-10] exploited the characteristics of cerebrospinal fluid (CSF) in T1 and T2 sequences of MRI images. Nevertheless, in order to apply the trained classifiers, the differences among images need to be as small as possible due to the nature of classification. To address the issue, this paper reinvented the wheel to propose unsupervised segmentation method without requirement of training process. Based on the characteristic property of skewness, the proposed algorithm can also distinguish the finer details such as nerve roots from CSF. The experimental study further demonstrated the benefits of proposed framework.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3827-3832
Number of pages6
ISBN (Electronic)9781538666500
DOIs
Publication statusPublished - Jan 16 2019
Event2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018 - Miyazaki, Japan
Duration: Oct 7 2018Oct 10 2018

Publication series

NameProceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018

Conference

Conference2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018
CountryJapan
CityMiyazaki
Period10/7/1810/10/18

Fingerprint

Cerebrospinal fluid
Cerebrospinal Fluid
Spinal Stenosis
Spinal Canal
Canals
Magnetic resonance imaging
Learning algorithms
Learning systems
Wheels
Classifiers
Machine Learning
Classifier
Learning algorithm
Classification system
Skewness
Cross section
Machine learning
Experimental study
Segmentation

Keywords

  • Cerebro spinal Fluid
  • Lumbar spinal stenosis
  • Magnetic resonance image
  • Measure of skewness
  • Segmentation
  • Thresholding
  • Unsupervised

ASJC Scopus subject areas

  • Information Systems
  • Information Systems and Management
  • Health Informatics
  • Artificial Intelligence
  • Computer Networks and Communications
  • Human-Computer Interaction

Cite this

Lee, K. R., Yeh, Y. X., Wu, C. C., Lin, J., & Chiang, Y. H. (2019). Unsupervised Classification of Cerebrospinal Fluid by Statistical Indicators. In Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018 (pp. 3827-3832). [8616645] (Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SMC.2018.00648

Unsupervised Classification of Cerebrospinal Fluid by Statistical Indicators. / Lee, Kuan Ru; Yeh, Yi Xian; Wu, Chao Cheng; Lin, Jiannher; Chiang, Yung Hsiao.

Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 3827-3832 8616645 (Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018).

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

Lee, KR, Yeh, YX, Wu, CC, Lin, J & Chiang, YH 2019, Unsupervised Classification of Cerebrospinal Fluid by Statistical Indicators. in Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018., 8616645, Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018, Institute of Electrical and Electronics Engineers Inc., pp. 3827-3832, 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018, Miyazaki, Japan, 10/7/18. https://doi.org/10.1109/SMC.2018.00648
Lee KR, Yeh YX, Wu CC, Lin J, Chiang YH. Unsupervised Classification of Cerebrospinal Fluid by Statistical Indicators. In Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 3827-3832. 8616645. (Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018). https://doi.org/10.1109/SMC.2018.00648
Lee, Kuan Ru ; Yeh, Yi Xian ; Wu, Chao Cheng ; Lin, Jiannher ; Chiang, Yung Hsiao. / Unsupervised Classification of Cerebrospinal Fluid by Statistical Indicators. Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 3827-3832 (Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018).
@inproceedings{5c2a4238a1294f61a670565059b9b215,
title = "Unsupervised Classification of Cerebrospinal Fluid by Statistical Indicators",
abstract = "Cross section area (CSA) of spinal canal has been a crucial indicator for lumbar spinal stenosis (LSS), which remains the leading preoperative diagnosis for elder people. Recently, the machine learning algorithms have been investigated in[7-10] for automatic classification systems. The methods investigated in[7-10] exploited the characteristics of cerebrospinal fluid (CSF) in T1 and T2 sequences of MRI images. Nevertheless, in order to apply the trained classifiers, the differences among images need to be as small as possible due to the nature of classification. To address the issue, this paper reinvented the wheel to propose unsupervised segmentation method without requirement of training process. Based on the characteristic property of skewness, the proposed algorithm can also distinguish the finer details such as nerve roots from CSF. The experimental study further demonstrated the benefits of proposed framework.",
keywords = "Cerebro spinal Fluid, Lumbar spinal stenosis, Magnetic resonance image, Measure of skewness, Segmentation, Thresholding, Unsupervised",
author = "Lee, {Kuan Ru} and Yeh, {Yi Xian} and Wu, {Chao Cheng} and Jiannher Lin and Chiang, {Yung Hsiao}",
year = "2019",
month = "1",
day = "16",
doi = "10.1109/SMC.2018.00648",
language = "English",
series = "Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "3827--3832",
booktitle = "Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018",
address = "United States",

}

TY - GEN

T1 - Unsupervised Classification of Cerebrospinal Fluid by Statistical Indicators

AU - Lee, Kuan Ru

AU - Yeh, Yi Xian

AU - Wu, Chao Cheng

AU - Lin, Jiannher

AU - Chiang, Yung Hsiao

PY - 2019/1/16

Y1 - 2019/1/16

N2 - Cross section area (CSA) of spinal canal has been a crucial indicator for lumbar spinal stenosis (LSS), which remains the leading preoperative diagnosis for elder people. Recently, the machine learning algorithms have been investigated in[7-10] for automatic classification systems. The methods investigated in[7-10] exploited the characteristics of cerebrospinal fluid (CSF) in T1 and T2 sequences of MRI images. Nevertheless, in order to apply the trained classifiers, the differences among images need to be as small as possible due to the nature of classification. To address the issue, this paper reinvented the wheel to propose unsupervised segmentation method without requirement of training process. Based on the characteristic property of skewness, the proposed algorithm can also distinguish the finer details such as nerve roots from CSF. The experimental study further demonstrated the benefits of proposed framework.

AB - Cross section area (CSA) of spinal canal has been a crucial indicator for lumbar spinal stenosis (LSS), which remains the leading preoperative diagnosis for elder people. Recently, the machine learning algorithms have been investigated in[7-10] for automatic classification systems. The methods investigated in[7-10] exploited the characteristics of cerebrospinal fluid (CSF) in T1 and T2 sequences of MRI images. Nevertheless, in order to apply the trained classifiers, the differences among images need to be as small as possible due to the nature of classification. To address the issue, this paper reinvented the wheel to propose unsupervised segmentation method without requirement of training process. Based on the characteristic property of skewness, the proposed algorithm can also distinguish the finer details such as nerve roots from CSF. The experimental study further demonstrated the benefits of proposed framework.

KW - Cerebro spinal Fluid

KW - Lumbar spinal stenosis

KW - Magnetic resonance image

KW - Measure of skewness

KW - Segmentation

KW - Thresholding

KW - Unsupervised

UR - http://www.scopus.com/inward/record.url?scp=85062212491&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062212491&partnerID=8YFLogxK

U2 - 10.1109/SMC.2018.00648

DO - 10.1109/SMC.2018.00648

M3 - Conference contribution

AN - SCOPUS:85062212491

T3 - Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018

SP - 3827

EP - 3832

BT - Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -