Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
Comparative Analysis of Deep Neural Network and Texture-Based Classifiers for Recognition of Acute Stroke using Non-Contrast CT Images. / Nedel'ko, Victor; Kozinets, Roman; Tulupov, Andrey et al.
Proceedings - 2020 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 376-379 9117784 (Proceedings - 2020 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2020).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
}
TY - GEN
T1 - Comparative Analysis of Deep Neural Network and Texture-Based Classifiers for Recognition of Acute Stroke using Non-Contrast CT Images
AU - Nedel'ko, Victor
AU - Kozinets, Roman
AU - Tulupov, Andrey
AU - Berikov, Vladimir
PY - 2020/5/1
Y1 - 2020/5/1
N2 - This work presents a computer technology for automatic recognition of acute stroke using non-contrast computed tomography brain images. The early diagnosis of acute stroke is of primary importance for deciding on a method for further treatment, and the developed system aims at assisting a radiology specialist in the decision making process. We consider deep neural network and texture-based classifiers in order to compare their efficiency on a moderate-sized sample of patients with acute stroke. We use U-net as a basic architecture of the neural network, and Haralick textural features, extracted from images, for kNN, SVM, Random Forest and Adaboost classifiers. Experiments with real CT images using cross-validation technique show that deep neural network outperforms the considered texture-based classifiers; however, the latter are faster in training. We demonstrate that texture-based approach is able to give potentially useful additional information for stroke recognition, such as estimates of textural features importance; visualization of differences in positive and negative class distributions.
AB - This work presents a computer technology for automatic recognition of acute stroke using non-contrast computed tomography brain images. The early diagnosis of acute stroke is of primary importance for deciding on a method for further treatment, and the developed system aims at assisting a radiology specialist in the decision making process. We consider deep neural network and texture-based classifiers in order to compare their efficiency on a moderate-sized sample of patients with acute stroke. We use U-net as a basic architecture of the neural network, and Haralick textural features, extracted from images, for kNN, SVM, Random Forest and Adaboost classifiers. Experiments with real CT images using cross-validation technique show that deep neural network outperforms the considered texture-based classifiers; however, the latter are faster in training. We demonstrate that texture-based approach is able to give potentially useful additional information for stroke recognition, such as estimates of textural features importance; visualization of differences in positive and negative class distributions.
KW - acute stroke
KW - classification
KW - deep neural network
KW - texture segmentation
KW - U-net
UR - http://www.scopus.com/inward/record.url?scp=85089658891&partnerID=8YFLogxK
U2 - 10.1109/USBEREIT48449.2020.9117784
DO - 10.1109/USBEREIT48449.2020.9117784
M3 - Conference contribution
AN - SCOPUS:85089658891
T3 - Proceedings - 2020 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2020
SP - 376
EP - 379
BT - Proceedings - 2020 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2020
Y2 - 14 May 2020 through 15 May 2020
ER -
ID: 25288711