Comparative Analysis of Deep Neural Network and Texture-Based Classifiers for Recognition of Acute Stroke using Non-Contrast CT Images

Comparative Analysis of Deep Neural Network and Texture-Based Classifiers for Recognition of Acute Stroke using Non-Contrast CT Images Full article

Conference

Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology
14-15 May 2020 , Екатеринбург

Source

Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology
Compilation, IEEE. 2020. 383 c.

Output data

Year: 2020, Article number : 9117784, Pages count : 4 DOI: 10.1109/USBEREIT48449.2020.9117784

Tags

acute stroke; classification; deep neural network; texture segmentation; U-net

Authors

Nedel'ko V. ¹ , Kozinets R. ² , Tulupov A. ³ , Berikov V. ¹

Affiliations

1	Sobolev Institute of Mathematics Sb Ras, Data Analysis Laboratory, Novosibirsk, Russian Federation
2	Novosibirsk State University, Department of Mechanics and Mathematics, Novosibirsk, Russian Federation
3	International Tomography Center Sb Ras, Mrt Technology Laboratory, Novosibirsk, Russian Federation

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. © 2020 IEEE.

Nedel'ko V. , Kozinets R. , Tulupov A. , Berikov V.
Comparative Analysis of Deep Neural Network and Texture-Based Classifiers for Recognition of Acute Stroke using Non-Contrast CT Images
In compilation Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology. – IEEE., 2020. – C.376-379. DOI: 10.1109/USBEREIT48449.2020.9117784 Scopus OpenAlex

Scopus:	2-s2.0-85089658891
OpenAlex:	W3036694159

DB	Citing
Scopus	6
OpenAlex	6