Predicting the Type of Tumor-Related Epilepsy in Patients With Low-Grade Gliomas: A Radiomics Study
Purpose: The majority of patients with low-grade gliomas (LGGs) experience tumor-related epilepsy during the disease course. Our study aimed to build a radiomic prediction model for LGG-related epilepsy type based on magnetic resonance imaging (MRI) data.Methods: A total of 205 cases with LGG-relate...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-03-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fonc.2020.00235/full |
| _version_ | 1818954277147639808 |
|---|---|
| author | Yinyan Wang Wei Wei Wei Wei Wei Wei Wei Wei Zhenyu Liu Zhenyu Liu Yuchao Liang Xing Liu Yiming Li Yiming Li Zhenchao Tang Zhenchao Tang Tao Jiang Tao Jiang Tao Jiang Tao Jiang Jie Tian Jie Tian Jie Tian Jie Tian |
| author_facet | Yinyan Wang Wei Wei Wei Wei Wei Wei Wei Wei Zhenyu Liu Zhenyu Liu Yuchao Liang Xing Liu Yiming Li Yiming Li Zhenchao Tang Zhenchao Tang Tao Jiang Tao Jiang Tao Jiang Tao Jiang Jie Tian Jie Tian Jie Tian Jie Tian |
| author_sort | Yinyan Wang |
| collection | DOAJ |
| description | Purpose: The majority of patients with low-grade gliomas (LGGs) experience tumor-related epilepsy during the disease course. Our study aimed to build a radiomic prediction model for LGG-related epilepsy type based on magnetic resonance imaging (MRI) data.Methods: A total of 205 cases with LGG-related epilepsy were enrolled in the retrospective study and divided into training and validation cohorts (1:1) according to their surgery time. Seven hundred thirty-four radiomic features were extracted from T2-weighted imaging, including six location features. Pearson correlation coefficient, univariate area under curve (AUC) analysis, and least absolute shrinkage and selection operator regression were adopted to select the most relevant features for the epilepsy type to build a radiomic signature. Furthermore, a novel radiomic nomogram was developed for clinical application using the radiomic signature and clinical variables from all patients.Results: Four MRI-based features were selected from the 734 radiomic features, including one location feature. Good discriminative performances were achieved in both training (AUC = 0.859, 95% CI = 0.787–0.932) and validation cohorts (AUC = 0.839, 95% CI = 0.761–0.917) for the type of epilepsy. The accuracies were 80.4 and 80.6%, respectively. The radiomic nomogram also allowed for a high degree of discrimination. All models presented favorable calibration curves and decision curve analyses.Conclusion: Our results suggested that the MRI-based radiomic analysis may predict the type of LGG-related epilepsy to enable individualized therapy for patients with LGG-related epilepsy. |
| first_indexed | 2024-12-20T10:19:36Z |
| format | Article |
| id | doaj.art-4e3e00bcce84496fabb9da518c4675e9 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-12-20T10:19:36Z |
| publishDate | 2020-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-4e3e00bcce84496fabb9da518c4675e92022-12-21T19:43:56ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2020-03-011010.3389/fonc.2020.00235513402Predicting the Type of Tumor-Related Epilepsy in Patients With Low-Grade Gliomas: A Radiomics StudyYinyan Wang0Wei Wei1Wei Wei2Wei Wei3Wei Wei4Zhenyu Liu5Zhenyu Liu6Yuchao Liang7Xing Liu8Yiming Li9Yiming Li10Zhenchao Tang11Zhenchao Tang12Tao Jiang13Tao Jiang14Tao Jiang15Tao Jiang16Jie Tian17Jie Tian18Jie Tian19Jie Tian20Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaCAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaSchool of Electronics and Information, Xi'an Polytechnic University, Xi'an, ChinaBeijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Medicine, Beihang University, Beijing, ChinaEngineering Research Center of Molecular and Neuro Imaging of Ministry of Education, School of Life Science and Technology, Xidian University, Xi'an, ChinaCAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaSchool of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, ChinaBeijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Molecular Pathology, Beijing Neurosurgical Institute, Capital Medical University, Beijing, ChinaBeijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Molecular Pathology, Beijing Neurosurgical Institute, Capital Medical University, Beijing, ChinaCAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaBeijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Medicine, Beihang University, Beijing, ChinaBeijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Molecular Pathology, Beijing Neurosurgical Institute, Capital Medical University, Beijing, ChinaCenter of Brain Tumor, Beijing Institute for Brain Disorders, Beijing, ChinaChina National Clinical Research Center for Neurological Diseases, Beijing, ChinaCAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaBeijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Medicine, Beihang University, Beijing, ChinaEngineering Research Center of Molecular and Neuro Imaging of Ministry of Education, School of Life Science and Technology, Xidian University, Xi'an, ChinaSchool of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, ChinaPurpose: The majority of patients with low-grade gliomas (LGGs) experience tumor-related epilepsy during the disease course. Our study aimed to build a radiomic prediction model for LGG-related epilepsy type based on magnetic resonance imaging (MRI) data.Methods: A total of 205 cases with LGG-related epilepsy were enrolled in the retrospective study and divided into training and validation cohorts (1:1) according to their surgery time. Seven hundred thirty-four radiomic features were extracted from T2-weighted imaging, including six location features. Pearson correlation coefficient, univariate area under curve (AUC) analysis, and least absolute shrinkage and selection operator regression were adopted to select the most relevant features for the epilepsy type to build a radiomic signature. Furthermore, a novel radiomic nomogram was developed for clinical application using the radiomic signature and clinical variables from all patients.Results: Four MRI-based features were selected from the 734 radiomic features, including one location feature. Good discriminative performances were achieved in both training (AUC = 0.859, 95% CI = 0.787–0.932) and validation cohorts (AUC = 0.839, 95% CI = 0.761–0.917) for the type of epilepsy. The accuracies were 80.4 and 80.6%, respectively. The radiomic nomogram also allowed for a high degree of discrimination. All models presented favorable calibration curves and decision curve analyses.Conclusion: Our results suggested that the MRI-based radiomic analysis may predict the type of LGG-related epilepsy to enable individualized therapy for patients with LGG-related epilepsy.https://www.frontiersin.org/article/10.3389/fonc.2020.00235/fullepilepsy typelow-grade gliomasmachine learningradiomicsT2-weighted imaging |
| spellingShingle | Yinyan Wang Wei Wei Wei Wei Wei Wei Wei Wei Zhenyu Liu Zhenyu Liu Yuchao Liang Xing Liu Yiming Li Yiming Li Zhenchao Tang Zhenchao Tang Tao Jiang Tao Jiang Tao Jiang Tao Jiang Jie Tian Jie Tian Jie Tian Jie Tian Predicting the Type of Tumor-Related Epilepsy in Patients With Low-Grade Gliomas: A Radiomics Study Frontiers in Oncology epilepsy type low-grade gliomas machine learning radiomics T2-weighted imaging |
| title | Predicting the Type of Tumor-Related Epilepsy in Patients With Low-Grade Gliomas: A Radiomics Study |
| title_full | Predicting the Type of Tumor-Related Epilepsy in Patients With Low-Grade Gliomas: A Radiomics Study |
| title_fullStr | Predicting the Type of Tumor-Related Epilepsy in Patients With Low-Grade Gliomas: A Radiomics Study |
| title_full_unstemmed | Predicting the Type of Tumor-Related Epilepsy in Patients With Low-Grade Gliomas: A Radiomics Study |
| title_short | Predicting the Type of Tumor-Related Epilepsy in Patients With Low-Grade Gliomas: A Radiomics Study |
| title_sort | predicting the type of tumor related epilepsy in patients with low grade gliomas a radiomics study |
| topic | epilepsy type low-grade gliomas machine learning radiomics T2-weighted imaging |
| url | https://www.frontiersin.org/article/10.3389/fonc.2020.00235/full |
| work_keys_str_mv | AT yinyanwang predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT weiwei predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT weiwei predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT weiwei predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT weiwei predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT zhenyuliu predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT zhenyuliu predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT yuchaoliang predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT xingliu predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT yimingli predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT yimingli predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT zhenchaotang predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT zhenchaotang predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT taojiang predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT taojiang predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT taojiang predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT taojiang predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT jietian predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT jietian predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT jietian predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy AT jietian predictingthetypeoftumorrelatedepilepsyinpatientswithlowgradegliomasaradiomicsstudy |