Ischemic brain stroke detection from MRI image using logistic regression classifier

Md Shabuj Hossain; Subir Saha; Liton Chandra Paul; Rezaul Azim; Abdulla Al Suman

doi:10.1109/ICREST51555.2021.9331090

Ischemic brain stroke detection from MRI image using logistic regression classifier

Md Shabuj Hossain, Subir Saha, Liton Chandra Paul, Rezaul Azim, Abdulla Al Suman

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

4 Citations (Scopus)

Abstract

In this paper an efficient model for ischemic brain stroke detection from magnetic resonance imaging (MRI) using machine learning approach namely logistic regression classifier is proposed. The MRI images are pre-processed to reduce noise and converted into gray images. Then the stroke portions of the MRI gray images are segmented by using hue, saturation, and value (HSV) color threshold and the segmented stroke images are converted into binary images to reduce computational complexity. The stroke features namely mean hue, standard deviation, mean variance and area of affected lesion i.e. stroke portion have been extracted. Finally, logistic regression classifier is used to identify the classes of test image. The proposed model shows an accuracy of 96%, sensitivity of 92.3% and specificity of 100% for testing datasets.

Original language	English
Title of host publication	ICREST 2021
Subtitle of host publication	2nd International Conference on Robotics, Electrical and Signal Processing Techniques
Place of Publication	Bangladesh
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	763-767
Number of pages	5
ISBN (Electronic)	9780738130408, 9781665415767
ISBN (Print)	9781665415774
DOIs	https://doi.org/10.1109/ICREST51555.2021.9331090
Publication status	Published - 5 Jan 2021
Externally published	Yes
Event	2nd International Conference on Robotics, Electrical and Signal Processing Techniques, ICREST 2021 - Virtual Event, Bangladesh Duration: 5 Jan 2021 → 7 Jan 2021

Conference

Conference	2nd International Conference on Robotics, Electrical and Signal Processing Techniques, ICREST 2021
Country/Territory	Bangladesh
Period	5/01/21 → 7/01/21

Keywords

Brain stroke detection
HSV color space
Logistic regression classifier
Machine learning
MRI

Access to Document

10.1109/ICREST51555.2021.9331090

Cite this

Hossain, M. S., Saha, S., Paul, L. C., Azim, R., & Al Suman, A. (2021). Ischemic brain stroke detection from MRI image using logistic regression classifier. In ICREST 2021: 2nd International Conference on Robotics, Electrical and Signal Processing Techniques (pp. 763-767). Article 9331090 Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICREST51555.2021.9331090

@inproceedings{fa5544fc33ac408181858ae7c60db2c2,

title = "Ischemic brain stroke detection from MRI image using logistic regression classifier",

abstract = "In this paper an efficient model for ischemic brain stroke detection from magnetic resonance imaging (MRI) using machine learning approach namely logistic regression classifier is proposed. The MRI images are pre-processed to reduce noise and converted into gray images. Then the stroke portions of the MRI gray images are segmented by using hue, saturation, and value (HSV) color threshold and the segmented stroke images are converted into binary images to reduce computational complexity. The stroke features namely mean hue, standard deviation, mean variance and area of affected lesion i.e. stroke portion have been extracted. Finally, logistic regression classifier is used to identify the classes of test image. The proposed model shows an accuracy of 96%, sensitivity of 92.3% and specificity of 100% for testing datasets.",

keywords = "Brain stroke detection, HSV color space, Logistic regression classifier, Machine learning, MRI",

author = "Hossain, {Md Shabuj} and Subir Saha and Paul, {Liton Chandra} and Rezaul Azim and {Al Suman}, Abdulla",

year = "2021",

month = jan,

day = "5",

doi = "10.1109/ICREST51555.2021.9331090",

language = "English",

isbn = "9781665415774",

pages = "763--767",

booktitle = "ICREST 2021",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "2nd International Conference on Robotics, Electrical and Signal Processing Techniques, ICREST 2021 ; Conference date: 05-01-2021 Through 07-01-2021",

}

Hossain, MS, Saha, S, Paul, LC, Azim, R & Al Suman, A 2021, Ischemic brain stroke detection from MRI image using logistic regression classifier. in ICREST 2021: 2nd International Conference on Robotics, Electrical and Signal Processing Techniques., 9331090, Institute of Electrical and Electronics Engineers (IEEE), Bangladesh, pp. 763-767, 2nd International Conference on Robotics, Electrical and Signal Processing Techniques, ICREST 2021, Bangladesh, 5/01/21. https://doi.org/10.1109/ICREST51555.2021.9331090

Ischemic brain stroke detection from MRI image using logistic regression classifier. / Hossain, Md Shabuj; Saha, Subir; Paul, Liton Chandra et al.
ICREST 2021: 2nd International Conference on Robotics, Electrical and Signal Processing Techniques. Bangladesh: Institute of Electrical and Electronics Engineers (IEEE), 2021. p. 763-767 9331090.

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

TY - GEN

T1 - Ischemic brain stroke detection from MRI image using logistic regression classifier

AU - Hossain, Md Shabuj

AU - Saha, Subir

AU - Paul, Liton Chandra

AU - Azim, Rezaul

AU - Al Suman, Abdulla

PY - 2021/1/5

Y1 - 2021/1/5

N2 - In this paper an efficient model for ischemic brain stroke detection from magnetic resonance imaging (MRI) using machine learning approach namely logistic regression classifier is proposed. The MRI images are pre-processed to reduce noise and converted into gray images. Then the stroke portions of the MRI gray images are segmented by using hue, saturation, and value (HSV) color threshold and the segmented stroke images are converted into binary images to reduce computational complexity. The stroke features namely mean hue, standard deviation, mean variance and area of affected lesion i.e. stroke portion have been extracted. Finally, logistic regression classifier is used to identify the classes of test image. The proposed model shows an accuracy of 96%, sensitivity of 92.3% and specificity of 100% for testing datasets.

AB - In this paper an efficient model for ischemic brain stroke detection from magnetic resonance imaging (MRI) using machine learning approach namely logistic regression classifier is proposed. The MRI images are pre-processed to reduce noise and converted into gray images. Then the stroke portions of the MRI gray images are segmented by using hue, saturation, and value (HSV) color threshold and the segmented stroke images are converted into binary images to reduce computational complexity. The stroke features namely mean hue, standard deviation, mean variance and area of affected lesion i.e. stroke portion have been extracted. Finally, logistic regression classifier is used to identify the classes of test image. The proposed model shows an accuracy of 96%, sensitivity of 92.3% and specificity of 100% for testing datasets.

KW - Brain stroke detection

KW - HSV color space

KW - Logistic regression classifier

KW - Machine learning

KW - MRI

UR - http://www.scopus.com/inward/record.url?scp=85100780160&partnerID=8YFLogxK

U2 - 10.1109/ICREST51555.2021.9331090

DO - 10.1109/ICREST51555.2021.9331090

M3 - Conference proceeding contribution

AN - SCOPUS:85100780160

SN - 9781665415774

SP - 763

EP - 767

BT - ICREST 2021

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Bangladesh

T2 - 2nd International Conference on Robotics, Electrical and Signal Processing Techniques, ICREST 2021

Y2 - 5 January 2021 through 7 January 2021

ER -

Hossain MS, Saha S, Paul LC, Azim R, Al Suman A. Ischemic brain stroke detection from MRI image using logistic regression classifier. In ICREST 2021: 2nd International Conference on Robotics, Electrical and Signal Processing Techniques. Bangladesh: Institute of Electrical and Electronics Engineers (IEEE). 2021. p. 763-767. 9331090 doi: 10.1109/ICREST51555.2021.9331090

Ischemic brain stroke detection from MRI image using logistic regression classifier

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this