TY - JOUR
T1 - Classification of brain strokes using divergence-based convolutional neural networks
AU - Polat, Özlem
AU - Dokur, Zümray
AU - Ölmez, Tamer
N1 - Publisher Copyright:
© 2024 Elsevier Ltd
PY - 2024/7
Y1 - 2024/7
N2 - Stroke is a cerebrovascular issue caused by reduced or interrupted blood flow to the brain, resulting in the rapid death of brain cells and potential permanent functional damage. Early detection, classification, and immediate intervention are essential to prevent severe consequences, including death or lifelong disabilities. In this study, a total of 6650 brain CT images were used, which included 1130 ischemic stroke, 1093 hemorrhagic stroke, and 4427 non-stroke cases provided by the Turkish Ministry of Health. The study first aimed to determine the presence of stroke in the brain. Secondly, in cases where stroke was detected, the type of stroke, whether ischemic or hemorrhagic, was determined. Lastly, the images were classified into three categories: non-stroke, hemorrhagic, and ischemic. A newly introduced divergence-based deep neural network (DNN) was modified and utilized for the method. Features were extracted from the convolutional neural network (CNN) using Walsh matrices, and classification was performed using the minimum distance network (MDN). Experimental results showed that when the images were binary classified as stroke vs. non-stroke and ischemic vs. hemorrhagic type, they achieved accuracies of 99.248% and 99.324%, respectively. For the three-class classification (non-stroke, ischemic, and hemorrhagic), a success rate of 99.097% was achieved. The proposed study has advantages in terms of no preprocessing stage, classification with real images without data augmentation, and the low number of parameters in the employed network. The results indicate that the proposed network successfully detects the presence and type of stroke with high accuracy and outperforms existing studies in the literature.
AB - Stroke is a cerebrovascular issue caused by reduced or interrupted blood flow to the brain, resulting in the rapid death of brain cells and potential permanent functional damage. Early detection, classification, and immediate intervention are essential to prevent severe consequences, including death or lifelong disabilities. In this study, a total of 6650 brain CT images were used, which included 1130 ischemic stroke, 1093 hemorrhagic stroke, and 4427 non-stroke cases provided by the Turkish Ministry of Health. The study first aimed to determine the presence of stroke in the brain. Secondly, in cases where stroke was detected, the type of stroke, whether ischemic or hemorrhagic, was determined. Lastly, the images were classified into three categories: non-stroke, hemorrhagic, and ischemic. A newly introduced divergence-based deep neural network (DNN) was modified and utilized for the method. Features were extracted from the convolutional neural network (CNN) using Walsh matrices, and classification was performed using the minimum distance network (MDN). Experimental results showed that when the images were binary classified as stroke vs. non-stroke and ischemic vs. hemorrhagic type, they achieved accuracies of 99.248% and 99.324%, respectively. For the three-class classification (non-stroke, ischemic, and hemorrhagic), a success rate of 99.097% was achieved. The proposed study has advantages in terms of no preprocessing stage, classification with real images without data augmentation, and the low number of parameters in the employed network. The results indicate that the proposed network successfully detects the presence and type of stroke with high accuracy and outperforms existing studies in the literature.
KW - Brain stroke
KW - Deep neural networks
KW - Image classification
KW - Walsh matrix
UR - http://www.scopus.com/inward/record.url?scp=85187223635&partnerID=8YFLogxK
U2 - 10.1016/j.bspc.2024.106193
DO - 10.1016/j.bspc.2024.106193
M3 - Article
AN - SCOPUS:85187223635
SN - 1746-8094
VL - 93
JO - Biomedical Signal Processing and Control
JF - Biomedical Signal Processing and Control
M1 - 106193
ER -