VGGNet-16 Convolutional Neural Network for Classification Of Stroke Based On CT Scan Images

DOI

10.2991/978-94-6463-364-1_104How to use a DOI?

Keywords

CNN; VGG; Stroke; Classification; CT Scan Image

Abstract

Stroke is a blood vessels disease, there is a process of sudden stoppage of blood from damaged blood vessels. Traditionally stroke is classified into two types, namely hemorrhagic rupture of blood vessels and ischemic Causes of strokes include blockages in blood vessels. This research aims to develop software that can automatically predict whether a CT scan image is an ischemic stroke or a hemorrhagic stroke. CT scan image data comes from the Haji Surabaya General Hospital which was taken during the January-May 2019 period and came from 110 patients who had indications of stroke. Before the image data is processed using the Convolutional Neural Network (CNN) algorithm using the VGGNet-16 architecture, the data goes through a preprocessing stage which aims to improve image quality including image conversion, Segmentation to remove skull, and augmentation, Gray scale. The next step is to determine the Convolutional Neural Network (CNN) parameters that will be used to carry out training data to obtain the best classification model. The best parameters in this experiment are Dropout with a value of 0.1, batch size with a value of 15, epoch with a value of 200, Optimizer is Adam, learning rate with a value of 0.0001, Loss function is Binary cross entropy, LR 2 with a value of 0.0001. The experimental results show that the Convolutional Neural Network (CNN) algorithm with the VGGNet-16 architecture produces the highest level of performance where the accuracy value is 99.62% for training data, and 99.5% for testing data.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Nur Sakinah
AU  - Muh Subhan
AU  - Tri Bata Biru Saputri
AU  - Tessy Badriah
AU  - Iwan Syarif
PY  - 2024
DA  - 2024/02/17
TI  - VGGNet-16 Convolutional Neural Network for Classification Of Stroke Based On CT Scan Images
BT  - Proceedings of the International Conference on Applied Science and Technology on Engineering Science 2023 (iCAST-ES 2023)
PB  - Atlantis Press
SP  - 1138
EP  - 1150
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-364-1_104
DO  - 10.2991/978-94-6463-364-1_104
ID  - Sakinah2024
ER  -