Convolutional Neural Networks For Identification Of Axial 2d Slices In Ct Data

Vavřinová, Pavlína

Convolutional Neural Networks For Identification Of Axial 2d Slices In Ct Data

Files

eeict2018-21.pdf(479.05 KB)

Date

2018

Authors

Vavřinová, Pavlína

Publisher

Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií

Abstract

This thesis deals with the classification of 2D axial slices in CT patient’s data. The classification is realized into six categories. The sphere of convolutional neural networks was used for this purpose and AlexNet network was specifically selected for the intention of this identification, which was applied to the created data set after being adaptated. The overall classification success rate was 84%. In addition, an analysis of mistakes in classification was performed.

Keywords

neural networks, deep learning, convolutional neural networks, AlexNet

Citation

Proceedings of the 24th Conference STUDENT EEICT 2018. s. 21-23. ISBN 978-80-214-5614-3
http://www.feec.vutbr.cz/EEICT/

Document type

Peer-reviewed

Document version

Published version

Language of document

cz

Document licence