An Application of Prior Knowledge on Detection of Brain Tumors in Magnetic Resonance Imaging Images

DOI

10.2991/978-2-494069-31-2_362How to use a DOI?

Keywords

Brain tumors; deep learning; prior knowledge; MRI images

Abstract

Brain diseases, such as brain tumors, are essential problems in people’s health. As a result, brain tumor detection has become a demanding and challenging task. In this paper, an interpretable method is proposed to introduce the prior knowledge of magnetic resonance imaging (MRI) images to brain tumor detection along with a pre-trained ResNeXt50(32×4d). Experiments are conducted over 7 different seeds and 6 different epochs. An outstanding accuracy of 95.13% was achieved on the test dataset. Compared with the traditional training method, this method improves the performance by 0.83% in the best case. Experimental results indicate that prior knowledge enhances performance on brain tumor detection by about 0.5% overall, proving that this method is useful and be of value for reference.

Copyright

© 2022 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  - Sicong Chen
PY  - 2022
DA  - 2022/12/29
TI  - An Application of Prior Knowledge on Detection of Brain Tumors in Magnetic Resonance Imaging Images
BT  - Proceedings of the 2022 6th International Seminar on Education, Management and Social Sciences (ISEMSS 2022)
PB  - Atlantis Press
SP  - 3087
EP  - 3094
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-494069-31-2_362
DO  - 10.2991/978-2-494069-31-2_362
ID  - Chen2022
ER  -