Correlation between multimodal radiographic features and preoperative seizure in brain tumor using machine learning
Tumor-related epilepsy (TRE) refers to the condition in which primary brain tumors cause recurring seizures. A model that classifies brain tumors as epileptogenic or non-epileptogenic could improve prognosis and treatment methods for TRE. This study aims to identify which MRI sequences and machine l...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Conference or Workshop Item |
Published: |
IEEE
2022
|
Subjects: | |
Online Access: | http://eprints.um.edu.my/46293/ https://doi.org/10.1109/IECBES54088.2022.10079242 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.um.eprints.46293 |
---|---|
record_format |
eprints |
spelling |
my.um.eprints.462932024-07-16T06:58:36Z http://eprints.um.edu.my/46293/ Correlation between multimodal radiographic features and preoperative seizure in brain tumor using machine learning George, Reuben Chow, Li Sze Lim, Kheng Seang Tan, Li Kuo Ramli, Norlisah QA75 Electronic computers. Computer science RC0254 Neoplasms. Tumors. Oncology (including Cancer) Tumor-related epilepsy (TRE) refers to the condition in which primary brain tumors cause recurring seizures. A model that classifies brain tumors as epileptogenic or non-epileptogenic could improve prognosis and treatment methods for TRE. This study aims to identify which MRI sequences and machine learning algorithms (MLAs) could be used to build the most accurate epileptogenic tumor classification model. T1W, T2W, T2W FLAIR and T1W contrast-enhanced scans were acquired from 24 glioma patients, 8 with and 16 without pre- operative epilepsy. A total of 88 features were extracted from the MRI sequences, including tumor location, volume, and several first order textural features derived from gray level cooccurrence matrices (GLCM). Each feature was then used as a predicting variable for 9 MLAs (7 variants of support vector machines (SVMs) and 2 variants of logistic regression) to construct classification models. The top 11 classification models had testing accuracies above or equal to 75%. These models all used SVM variants instead of logistic regression variants. The classification model that used tumor location, and the one that used tumor volume, had testing accuracies of 100% and 87.5% respectively. The 9 other top classification models used GLCM features extracted from the contrast T1W sequence. IEEE 2022 Conference or Workshop Item PeerReviewed George, Reuben and Chow, Li Sze and Lim, Kheng Seang and Tan, Li Kuo and Ramli, Norlisah (2022) Correlation between multimodal radiographic features and preoperative seizure in brain tumor using machine learning. In: 2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences, LECBES, 07-09 December 2022, Kuala Lumpur. https://doi.org/10.1109/IECBES54088.2022.10079242 |
institution |
Universiti Malaya |
building |
UM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaya |
content_source |
UM Research Repository |
url_provider |
http://eprints.um.edu.my/ |
topic |
QA75 Electronic computers. Computer science RC0254 Neoplasms. Tumors. Oncology (including Cancer) |
spellingShingle |
QA75 Electronic computers. Computer science RC0254 Neoplasms. Tumors. Oncology (including Cancer) George, Reuben Chow, Li Sze Lim, Kheng Seang Tan, Li Kuo Ramli, Norlisah Correlation between multimodal radiographic features and preoperative seizure in brain tumor using machine learning |
description |
Tumor-related epilepsy (TRE) refers to the condition in which primary brain tumors cause recurring seizures. A model that classifies brain tumors as epileptogenic or non-epileptogenic could improve prognosis and treatment methods for TRE. This study aims to identify which MRI sequences and machine learning algorithms (MLAs) could be used to build the most accurate epileptogenic tumor classification model. T1W, T2W, T2W FLAIR and T1W contrast-enhanced scans were acquired from 24 glioma patients, 8 with and 16 without pre- operative epilepsy. A total of 88 features were extracted from the MRI sequences, including tumor location, volume, and several first order textural features derived from gray level cooccurrence matrices (GLCM). Each feature was then used as a predicting variable for 9 MLAs (7 variants of support vector machines (SVMs) and 2 variants of logistic regression) to construct classification models. The top 11 classification models had testing accuracies above or equal to 75%. These models all used SVM variants instead of logistic regression variants. The classification model that used tumor location, and the one that used tumor volume, had testing accuracies of 100% and 87.5% respectively. The 9 other top classification models used GLCM features extracted from the contrast T1W sequence. |
format |
Conference or Workshop Item |
author |
George, Reuben Chow, Li Sze Lim, Kheng Seang Tan, Li Kuo Ramli, Norlisah |
author_facet |
George, Reuben Chow, Li Sze Lim, Kheng Seang Tan, Li Kuo Ramli, Norlisah |
author_sort |
George, Reuben |
title |
Correlation between multimodal radiographic features and preoperative seizure in brain tumor using machine learning |
title_short |
Correlation between multimodal radiographic features and preoperative seizure in brain tumor using machine learning |
title_full |
Correlation between multimodal radiographic features and preoperative seizure in brain tumor using machine learning |
title_fullStr |
Correlation between multimodal radiographic features and preoperative seizure in brain tumor using machine learning |
title_full_unstemmed |
Correlation between multimodal radiographic features and preoperative seizure in brain tumor using machine learning |
title_sort |
correlation between multimodal radiographic features and preoperative seizure in brain tumor using machine learning |
publisher |
IEEE |
publishDate |
2022 |
url |
http://eprints.um.edu.my/46293/ https://doi.org/10.1109/IECBES54088.2022.10079242 |
_version_ |
1805881185249787904 |
score |
13.18916 |