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 -