Radiomics for the Prediction of Epilepsy in Patients With Frontal Glioma

ObjectiveThis study was conducted in order to investigate the association between radiomics features and frontal glioma-associated epilepsy (GAE) and propose a reliable radiomics-based model to predict frontal GAE.MethodsThis retrospective study consecutively enrolled 166 adult patients with frontal...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ankang Gao, Hongxi Yang, Yida Wang, Guohua Zhao, Chenglong Wang, Haijie Wang, Xiaonan Zhang, Yong Zhang, Jingliang Cheng, Guang Yang, Jie Bai
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	radiomics glioma glioma-associated epilepsy frontal lobe epilepsy T2 fluid-attenuated inversion recovery Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
Acceso en línea:	https://doaj.org/article/a48d34721e2c428588c5e0bead78dbd5
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a48d34721e2c428588c5e0bead78dbd5
record_format	dspace
spelling	oai:doaj.org-article:a48d34721e2c428588c5e0bead78dbd52021-11-22T05:19:02ZRadiomics for the Prediction of Epilepsy in Patients With Frontal Glioma2234-943X10.3389/fonc.2021.725926https://doaj.org/article/a48d34721e2c428588c5e0bead78dbd52021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fonc.2021.725926/fullhttps://doaj.org/toc/2234-943XObjectiveThis study was conducted in order to investigate the association between radiomics features and frontal glioma-associated epilepsy (GAE) and propose a reliable radiomics-based model to predict frontal GAE.MethodsThis retrospective study consecutively enrolled 166 adult patients with frontal glioma (111 in the training cohort and 55 in the testing cohort). A total 1,130 features were extracted from T2 fluid-attenuated inversion recovery images, including first-order statistics, 3D shape, texture, and wavelet features. Regions of interest, including the entire tumor and peritumoral edema, were drawn manually. Pearson correlation coefficient, 10-fold cross-validation, area under curve (AUC) analysis, and support vector machine were adopted to select the most relevant features to build a clinical model, a radiomics model, and a clinical–radiomics model for GAE. The receiver operating characteristic curve (ROC) and AUC were used to evaluate the classification performance of the models in each cohort, and DeLong’s test was used to compare the performance of the models. A two-sided t-test and Fisher’s exact test were used to compare the clinical variables. Statistical analysis was performed using SPSS software (version 22.0; IBM, Armonk, New York), and p <0.05 was set as the threshold for significance.ResultsThe classification accuracy of seven scout models, except the wavelet first-order model (0.793) and the wavelet texture model (0.784), was <0.75 in cross-validation. The clinical–radiomics model, including 17 magnetic resonance imaging-based features selected among the 1,130 radiomics features and two clinical features (patient age and tumor grade), achieved better discriminative performance for GAE prediction in both the training [AUC = 0.886, 95% confidence interval (CI) = 0.819–0.940] and testing cohorts (AUC = 0.836, 95% CI = 0.707–0.937) than the radiomics model (p = 0.008) with 82.0% and 78.2% accuracy, respectively.ConclusionRadiomics analysis can non-invasively predict GAE, thus allowing adequate treatment of frontal glioma. The clinical–radiomics model may enable a more precise prediction of frontal GAE. Furthermore, age and pathology grade are important risk factors for GAE.Ankang GaoHongxi YangYida WangGuohua ZhaoChenglong WangHaijie WangXiaonan ZhangYong ZhangJingliang ChengGuang YangJie BaiFrontiers Media S.A.articleradiomicsgliomaglioma-associated epilepsyfrontal lobe epilepsyT2 fluid-attenuated inversion recoveryNeoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENFrontiers in Oncology, Vol 11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	radiomics glioma glioma-associated epilepsy frontal lobe epilepsy T2 fluid-attenuated inversion recovery Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
spellingShingle	radiomics glioma glioma-associated epilepsy frontal lobe epilepsy T2 fluid-attenuated inversion recovery Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282 Ankang Gao Hongxi Yang Yida Wang Guohua Zhao Chenglong Wang Haijie Wang Xiaonan Zhang Yong Zhang Jingliang Cheng Guang Yang Jie Bai Radiomics for the Prediction of Epilepsy in Patients With Frontal Glioma
description	ObjectiveThis study was conducted in order to investigate the association between radiomics features and frontal glioma-associated epilepsy (GAE) and propose a reliable radiomics-based model to predict frontal GAE.MethodsThis retrospective study consecutively enrolled 166 adult patients with frontal glioma (111 in the training cohort and 55 in the testing cohort). A total 1,130 features were extracted from T2 fluid-attenuated inversion recovery images, including first-order statistics, 3D shape, texture, and wavelet features. Regions of interest, including the entire tumor and peritumoral edema, were drawn manually. Pearson correlation coefficient, 10-fold cross-validation, area under curve (AUC) analysis, and support vector machine were adopted to select the most relevant features to build a clinical model, a radiomics model, and a clinical–radiomics model for GAE. The receiver operating characteristic curve (ROC) and AUC were used to evaluate the classification performance of the models in each cohort, and DeLong’s test was used to compare the performance of the models. A two-sided t-test and Fisher’s exact test were used to compare the clinical variables. Statistical analysis was performed using SPSS software (version 22.0; IBM, Armonk, New York), and p <0.05 was set as the threshold for significance.ResultsThe classification accuracy of seven scout models, except the wavelet first-order model (0.793) and the wavelet texture model (0.784), was <0.75 in cross-validation. The clinical–radiomics model, including 17 magnetic resonance imaging-based features selected among the 1,130 radiomics features and two clinical features (patient age and tumor grade), achieved better discriminative performance for GAE prediction in both the training [AUC = 0.886, 95% confidence interval (CI) = 0.819–0.940] and testing cohorts (AUC = 0.836, 95% CI = 0.707–0.937) than the radiomics model (p = 0.008) with 82.0% and 78.2% accuracy, respectively.ConclusionRadiomics analysis can non-invasively predict GAE, thus allowing adequate treatment of frontal glioma. The clinical–radiomics model may enable a more precise prediction of frontal GAE. Furthermore, age and pathology grade are important risk factors for GAE.
format	article
author	Ankang Gao Hongxi Yang Yida Wang Guohua Zhao Chenglong Wang Haijie Wang Xiaonan Zhang Yong Zhang Jingliang Cheng Guang Yang Jie Bai
author_facet	Ankang Gao Hongxi Yang Yida Wang Guohua Zhao Chenglong Wang Haijie Wang Xiaonan Zhang Yong Zhang Jingliang Cheng Guang Yang Jie Bai
author_sort	Ankang Gao
title	Radiomics for the Prediction of Epilepsy in Patients With Frontal Glioma
title_short	Radiomics for the Prediction of Epilepsy in Patients With Frontal Glioma
title_full	Radiomics for the Prediction of Epilepsy in Patients With Frontal Glioma
title_fullStr	Radiomics for the Prediction of Epilepsy in Patients With Frontal Glioma
title_full_unstemmed	Radiomics for the Prediction of Epilepsy in Patients With Frontal Glioma
title_sort	radiomics for the prediction of epilepsy in patients with frontal glioma
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/a48d34721e2c428588c5e0bead78dbd5
work_keys_str_mv	AT ankanggao radiomicsforthepredictionofepilepsyinpatientswithfrontalglioma AT hongxiyang radiomicsforthepredictionofepilepsyinpatientswithfrontalglioma AT yidawang radiomicsforthepredictionofepilepsyinpatientswithfrontalglioma AT guohuazhao radiomicsforthepredictionofepilepsyinpatientswithfrontalglioma AT chenglongwang radiomicsforthepredictionofepilepsyinpatientswithfrontalglioma AT haijiewang radiomicsforthepredictionofepilepsyinpatientswithfrontalglioma AT xiaonanzhang radiomicsforthepredictionofepilepsyinpatientswithfrontalglioma AT yongzhang radiomicsforthepredictionofepilepsyinpatientswithfrontalglioma AT jingliangcheng radiomicsforthepredictionofepilepsyinpatientswithfrontalglioma AT guangyang radiomicsforthepredictionofepilepsyinpatientswithfrontalglioma AT jiebai radiomicsforthepredictionofepilepsyinpatientswithfrontalglioma
_version_	1718418178749497344

Radiomics for the Prediction of Epilepsy in Patients With Frontal Glioma

Ejemplares similares