Development of computer aids ASPECTS system for acute ischemic stroke patient

A preliminary study

Jenn Lung Su, Lung Chan, S. Y. Huang

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

Abstract

In recent years, stroke ranked within the top ten leading causes of death and the incidence is still rising. As a result of clinical interpretation of Alberta Stroke Program Early CT Score (ASPECTS), the relevant personnel to define stroke area and score range are not consistent and cause difficulty to make treatment decision. This study was to develop a computer-aided scoring system for ischemic stroke patient to help doctors effectively determine the severity of ischemic stroke. Image processing technology was used to develop the system. First, an adaptive median filter was used to filter noise in computed tomography (CT) image, and then bi-level and regional growth methods were used to obtain effective image information. After texture parameters selection through t-test and support vector machine (SVM), regions of interesting (ROI) were automatically selected. Finally, the ischemic severity were obtained based on calculated ASPECTS score (by compared the left and right sides of the brain image). The CT images of 80 sets (40 training sets and 40 test sets) were used to evaluate the system by comparing with corresponding DWI-MRI. The results showed that the area under the ROC curve of the training sets and the test sets were 0.952 and 0.938, respectively, when four parameters (autocorrelation, variance, maximum probability, and homogeneity) were chosen. Accuracy was 0.90, sensitivity was 0.76, specificity was 1, and Kappa value was 0.52 for test data respectively, and the performance was superior to the physician group.

Original languageEnglish
Title of host publication2nd International Conference for Innovation in Biomedical Engineering and Life Sciences - ICIBEL 2017 in conjunction with APCMBE 2017
PublisherSpringer Verlag
Pages203-207
Number of pages5
Volume67
ISBN (Print)9789811075537
DOIs
Publication statusPublished - Jan 1 2018
Event2nd International Conference for Innovation in Biomedical Engineering and Life Sciences, ICIBEL 2017, held in conjunction with the 10th Asia Pacific Conference on Medical and Biological Engineering, APCMBE 2017 - Penang, Malaysia
Duration: Dec 10 2017Dec 13 2017

Conference

Conference2nd International Conference for Innovation in Biomedical Engineering and Life Sciences, ICIBEL 2017, held in conjunction with the 10th Asia Pacific Conference on Medical and Biological Engineering, APCMBE 2017
CountryMalaysia
CityPenang
Period12/10/1712/13/17

Fingerprint

Tomography
Computer systems
Median filters
Adaptive filters
Autocorrelation
Magnetic resonance imaging
Support vector machines
Brain
Image processing
Textures
Personnel

Keywords

  • Acute ischemic stroke
  • ASPECTS
  • CT images
  • Texture parameters

ASJC Scopus subject areas

  • Bioengineering
  • Biomedical Engineering

Cite this

Su, J. L., Chan, L., & Huang, S. Y. (2018). Development of computer aids ASPECTS system for acute ischemic stroke patient: A preliminary study. In 2nd International Conference for Innovation in Biomedical Engineering and Life Sciences - ICIBEL 2017 in conjunction with APCMBE 2017 (Vol. 67, pp. 203-207). Springer Verlag. https://doi.org/10.1007/978-981-10-7554-4_35

Development of computer aids ASPECTS system for acute ischemic stroke patient : A preliminary study. / Su, Jenn Lung; Chan, Lung; Huang, S. Y.

2nd International Conference for Innovation in Biomedical Engineering and Life Sciences - ICIBEL 2017 in conjunction with APCMBE 2017. Vol. 67 Springer Verlag, 2018. p. 203-207.

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

Su, JL, Chan, L & Huang, SY 2018, Development of computer aids ASPECTS system for acute ischemic stroke patient: A preliminary study. in 2nd International Conference for Innovation in Biomedical Engineering and Life Sciences - ICIBEL 2017 in conjunction with APCMBE 2017. vol. 67, Springer Verlag, pp. 203-207, 2nd International Conference for Innovation in Biomedical Engineering and Life Sciences, ICIBEL 2017, held in conjunction with the 10th Asia Pacific Conference on Medical and Biological Engineering, APCMBE 2017, Penang, Malaysia, 12/10/17. https://doi.org/10.1007/978-981-10-7554-4_35
Su JL, Chan L, Huang SY. Development of computer aids ASPECTS system for acute ischemic stroke patient: A preliminary study. In 2nd International Conference for Innovation in Biomedical Engineering and Life Sciences - ICIBEL 2017 in conjunction with APCMBE 2017. Vol. 67. Springer Verlag. 2018. p. 203-207 https://doi.org/10.1007/978-981-10-7554-4_35
Su, Jenn Lung ; Chan, Lung ; Huang, S. Y. / Development of computer aids ASPECTS system for acute ischemic stroke patient : A preliminary study. 2nd International Conference for Innovation in Biomedical Engineering and Life Sciences - ICIBEL 2017 in conjunction with APCMBE 2017. Vol. 67 Springer Verlag, 2018. pp. 203-207
@inproceedings{e71b8891a2374654a1a3ecf1a36a05f4,
title = "Development of computer aids ASPECTS system for acute ischemic stroke patient: A preliminary study",
abstract = "In recent years, stroke ranked within the top ten leading causes of death and the incidence is still rising. As a result of clinical interpretation of Alberta Stroke Program Early CT Score (ASPECTS), the relevant personnel to define stroke area and score range are not consistent and cause difficulty to make treatment decision. This study was to develop a computer-aided scoring system for ischemic stroke patient to help doctors effectively determine the severity of ischemic stroke. Image processing technology was used to develop the system. First, an adaptive median filter was used to filter noise in computed tomography (CT) image, and then bi-level and regional growth methods were used to obtain effective image information. After texture parameters selection through t-test and support vector machine (SVM), regions of interesting (ROI) were automatically selected. Finally, the ischemic severity were obtained based on calculated ASPECTS score (by compared the left and right sides of the brain image). The CT images of 80 sets (40 training sets and 40 test sets) were used to evaluate the system by comparing with corresponding DWI-MRI. The results showed that the area under the ROC curve of the training sets and the test sets were 0.952 and 0.938, respectively, when four parameters (autocorrelation, variance, maximum probability, and homogeneity) were chosen. Accuracy was 0.90, sensitivity was 0.76, specificity was 1, and Kappa value was 0.52 for test data respectively, and the performance was superior to the physician group.",
keywords = "Acute ischemic stroke, ASPECTS, CT images, Texture parameters",
author = "Su, {Jenn Lung} and Lung Chan and Huang, {S. Y.}",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/978-981-10-7554-4_35",
language = "English",
isbn = "9789811075537",
volume = "67",
pages = "203--207",
booktitle = "2nd International Conference for Innovation in Biomedical Engineering and Life Sciences - ICIBEL 2017 in conjunction with APCMBE 2017",
publisher = "Springer Verlag",

}

TY - GEN

T1 - Development of computer aids ASPECTS system for acute ischemic stroke patient

T2 - A preliminary study

AU - Su, Jenn Lung

AU - Chan, Lung

AU - Huang, S. Y.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In recent years, stroke ranked within the top ten leading causes of death and the incidence is still rising. As a result of clinical interpretation of Alberta Stroke Program Early CT Score (ASPECTS), the relevant personnel to define stroke area and score range are not consistent and cause difficulty to make treatment decision. This study was to develop a computer-aided scoring system for ischemic stroke patient to help doctors effectively determine the severity of ischemic stroke. Image processing technology was used to develop the system. First, an adaptive median filter was used to filter noise in computed tomography (CT) image, and then bi-level and regional growth methods were used to obtain effective image information. After texture parameters selection through t-test and support vector machine (SVM), regions of interesting (ROI) were automatically selected. Finally, the ischemic severity were obtained based on calculated ASPECTS score (by compared the left and right sides of the brain image). The CT images of 80 sets (40 training sets and 40 test sets) were used to evaluate the system by comparing with corresponding DWI-MRI. The results showed that the area under the ROC curve of the training sets and the test sets were 0.952 and 0.938, respectively, when four parameters (autocorrelation, variance, maximum probability, and homogeneity) were chosen. Accuracy was 0.90, sensitivity was 0.76, specificity was 1, and Kappa value was 0.52 for test data respectively, and the performance was superior to the physician group.

AB - In recent years, stroke ranked within the top ten leading causes of death and the incidence is still rising. As a result of clinical interpretation of Alberta Stroke Program Early CT Score (ASPECTS), the relevant personnel to define stroke area and score range are not consistent and cause difficulty to make treatment decision. This study was to develop a computer-aided scoring system for ischemic stroke patient to help doctors effectively determine the severity of ischemic stroke. Image processing technology was used to develop the system. First, an adaptive median filter was used to filter noise in computed tomography (CT) image, and then bi-level and regional growth methods were used to obtain effective image information. After texture parameters selection through t-test and support vector machine (SVM), regions of interesting (ROI) were automatically selected. Finally, the ischemic severity were obtained based on calculated ASPECTS score (by compared the left and right sides of the brain image). The CT images of 80 sets (40 training sets and 40 test sets) were used to evaluate the system by comparing with corresponding DWI-MRI. The results showed that the area under the ROC curve of the training sets and the test sets were 0.952 and 0.938, respectively, when four parameters (autocorrelation, variance, maximum probability, and homogeneity) were chosen. Accuracy was 0.90, sensitivity was 0.76, specificity was 1, and Kappa value was 0.52 for test data respectively, and the performance was superior to the physician group.

KW - Acute ischemic stroke

KW - ASPECTS

KW - CT images

KW - Texture parameters

UR - http://www.scopus.com/inward/record.url?scp=85038087115&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85038087115&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-7554-4_35

DO - 10.1007/978-981-10-7554-4_35

M3 - Conference contribution

SN - 9789811075537

VL - 67

SP - 203

EP - 207

BT - 2nd International Conference for Innovation in Biomedical Engineering and Life Sciences - ICIBEL 2017 in conjunction with APCMBE 2017

PB - Springer Verlag

ER -