Multi‐view learning for benign epilepsy with centrotemporal spikes
Benign epilepsy with centrotemporal spikes (BECT) may be the most popular epilepsy to attack children. In recent years, more and more studies have shown that magnetic resonance imaging (MRI) and functional magnetic resonance imaging (fMRI) are promising techniques in distinguishing BECT patients fro...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-03-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2018.5162 |
| _version_ | 1797684289656061952 |
|---|---|
| author | Ming Yan Ling Liu Sunitha Basodi Yi Pan |
| author_facet | Ming Yan Ling Liu Sunitha Basodi Yi Pan |
| author_sort | Ming Yan |
| collection | DOAJ |
| description | Benign epilepsy with centrotemporal spikes (BECT) may be the most popular epilepsy to attack children. In recent years, more and more studies have shown that magnetic resonance imaging (MRI) and functional magnetic resonance imaging (fMRI) are promising techniques in distinguishing BECT patients from healthy controls. However, these existing works have suffered from two limitations. On the one hand, they have paid more attention to the brain changes between BETC and healthy controls than developing machine learning methods that can recognize BECT patients. On the other hand, most of the existing approaches extract hand‐crafted features from MRI or fMRI, which cannot obtain the desired performance due to the limited representative capacity of the used features. To address these issues, we propose a novel classification method by fusing the predictions of three different views: hand‐crafted features view, MRI view, and fMRI view. The final result is obtained by passing through those predictions after a fusing neural network. The basic idea of our method is that multiple views could provide complementary information and thus can boost the classification performance. Extensive experiments show that the proposed multi‐view method is remarkably superior to single‐view methods. |
| first_indexed | 2024-03-12T00:28:29Z |
| format | Article |
| id | doaj.art-b64b426e8f64427ea08180d2d54f1170 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:28:29Z |
| publishDate | 2019-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-b64b426e8f64427ea08180d2d54f11702023-09-15T10:31:50ZengWileyIET Computer Vision1751-96321751-96402019-03-0113210911610.1049/iet-cvi.2018.5162Multi‐view learning for benign epilepsy with centrotemporal spikesMing Yan0Ling Liu1Sunitha Basodi2Yi Pan3Machine Intelligence Laboratory, College of Computer Science, Sichuan UniversityChengduPeople's Republic of ChinaDepartment of neurologyWest China Hospital, Sichuan UniversityChengduPeople's Republic of ChinaDepartment of Computer ScienceGeorgia State UniversityAtlantaUSADepartment of Computer ScienceGeorgia State UniversityAtlantaUSABenign epilepsy with centrotemporal spikes (BECT) may be the most popular epilepsy to attack children. In recent years, more and more studies have shown that magnetic resonance imaging (MRI) and functional magnetic resonance imaging (fMRI) are promising techniques in distinguishing BECT patients from healthy controls. However, these existing works have suffered from two limitations. On the one hand, they have paid more attention to the brain changes between BETC and healthy controls than developing machine learning methods that can recognize BECT patients. On the other hand, most of the existing approaches extract hand‐crafted features from MRI or fMRI, which cannot obtain the desired performance due to the limited representative capacity of the used features. To address these issues, we propose a novel classification method by fusing the predictions of three different views: hand‐crafted features view, MRI view, and fMRI view. The final result is obtained by passing through those predictions after a fusing neural network. The basic idea of our method is that multiple views could provide complementary information and thus can boost the classification performance. Extensive experiments show that the proposed multi‐view method is remarkably superior to single‐view methods.https://doi.org/10.1049/iet-cvi.2018.5162machine learning methodsBECT patientsfMRImultiple viewsclassification performancemultiview method |
| spellingShingle | Ming Yan Ling Liu Sunitha Basodi Yi Pan Multi‐view learning for benign epilepsy with centrotemporal spikes IET Computer Vision machine learning methods BECT patients fMRI multiple views classification performance multiview method |
| title | Multi‐view learning for benign epilepsy with centrotemporal spikes |
| title_full | Multi‐view learning for benign epilepsy with centrotemporal spikes |
| title_fullStr | Multi‐view learning for benign epilepsy with centrotemporal spikes |
| title_full_unstemmed | Multi‐view learning for benign epilepsy with centrotemporal spikes |
| title_short | Multi‐view learning for benign epilepsy with centrotemporal spikes |
| title_sort | multi view learning for benign epilepsy with centrotemporal spikes |
| topic | machine learning methods BECT patients fMRI multiple views classification performance multiview method |
| url | https://doi.org/10.1049/iet-cvi.2018.5162 |
| work_keys_str_mv | AT mingyan multiviewlearningforbenignepilepsywithcentrotemporalspikes AT lingliu multiviewlearningforbenignepilepsywithcentrotemporalspikes AT sunithabasodi multiviewlearningforbenignepilepsywithcentrotemporalspikes AT yipan multiviewlearningforbenignepilepsywithcentrotemporalspikes |