CT Angiography-Based Radiomics for Classification of Intracranial Aneurysm Rupture

Background: Intracranial aneurysm rupture is a devastating medical event with a high morbidity and mortality rate. Thus, timely detection and management are critical. The present study aimed to identify the aneurysm radiomics features associated with rupture and to build and evaluate a radiomics cla...

Full description

Bibliographic Details
Main Authors: Osamah Alwalid, Xi Long, Mingfei Xie, Jiehua Yang, Chunyuan Cen, Huan Liu, Ping Han
Format: Article
Language:English
Published: Frontiers Media S.A. 2021-02-01
Series:Frontiers in Neurology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fneur.2021.619864/full
_version_ 1818877840533225472
author Osamah Alwalid
Osamah Alwalid
Xi Long
Xi Long
Mingfei Xie
Mingfei Xie
Jiehua Yang
Chunyuan Cen
Chunyuan Cen
Huan Liu
Ping Han
Ping Han
author_facet Osamah Alwalid
Osamah Alwalid
Xi Long
Xi Long
Mingfei Xie
Mingfei Xie
Jiehua Yang
Chunyuan Cen
Chunyuan Cen
Huan Liu
Ping Han
Ping Han
author_sort Osamah Alwalid
collection DOAJ
description Background: Intracranial aneurysm rupture is a devastating medical event with a high morbidity and mortality rate. Thus, timely detection and management are critical. The present study aimed to identify the aneurysm radiomics features associated with rupture and to build and evaluate a radiomics classification model of aneurysm rupture.Methods: Radiomics analysis was applied to CT angiography (CTA) images of 393 patients [152 (38.7%) with ruptured aneurysms]. Patients were divided at a ratio of 7:3 into retrospective training (n = 274) and prospective test (n = 119) cohorts. A total of 1,229 radiomics features were automatically calculated from each aneurysm. The feature number was systematically reduced, and the most important classifying features were selected. A logistic regression model was constructed using the selected features and evaluated on training and test cohorts. Radiomics score (Rad-score) was calculated for each patient and compared between ruptured and unruptured aneurysms.Results: Nine radiomics features were selected from the CTA images and used to build the logistic regression model. The radiomics model has shown good performance in the classification of the aneurysm rupture on training and test cohorts [area under the receiver operating characteristic curve: 0.92 [95% confidence interval CI: 0.89–0.95] and 0.86 [95% CI: 0.80–0.93], respectively, p < 0.001]. Rad-score showed statistically significant differences between ruptured and unruptured aneurysms (median, 2.50 vs. −1.60 and 2.35 vs. −1.01 on training and test cohorts, respectively, p < 0.001).Conclusion: The results indicated the potential of aneurysm radiomics features for automatic classification of aneurysm rupture on CTA images.
first_indexed 2024-12-19T14:04:41Z
format Article
id doaj.art-c31d1d8bf1ad406f92b09b2a28b32c19
institution Directory Open Access Journal
issn 1664-2295
language English
last_indexed 2024-12-19T14:04:41Z
publishDate 2021-02-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neurology
spelling doaj.art-c31d1d8bf1ad406f92b09b2a28b32c192022-12-21T20:18:21ZengFrontiers Media S.A.Frontiers in Neurology1664-22952021-02-011210.3389/fneur.2021.619864619864CT Angiography-Based Radiomics for Classification of Intracranial Aneurysm RuptureOsamah Alwalid0Osamah Alwalid1Xi Long2Xi Long3Mingfei Xie4Mingfei Xie5Jiehua Yang6Chunyuan Cen7Chunyuan Cen8Huan Liu9Ping Han10Ping Han11Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaHubei Province Key Laboratory of Molecular Imaging, Wuhan, ChinaDepartment of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaHubei Province Key Laboratory of Molecular Imaging, Wuhan, ChinaDepartment of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaHubei Province Key Laboratory of Molecular Imaging, Wuhan, ChinaSchool of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaHubei Province Key Laboratory of Molecular Imaging, Wuhan, ChinaGE Healthcare, Shanghai, ChinaDepartment of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaHubei Province Key Laboratory of Molecular Imaging, Wuhan, ChinaBackground: Intracranial aneurysm rupture is a devastating medical event with a high morbidity and mortality rate. Thus, timely detection and management are critical. The present study aimed to identify the aneurysm radiomics features associated with rupture and to build and evaluate a radiomics classification model of aneurysm rupture.Methods: Radiomics analysis was applied to CT angiography (CTA) images of 393 patients [152 (38.7%) with ruptured aneurysms]. Patients were divided at a ratio of 7:3 into retrospective training (n = 274) and prospective test (n = 119) cohorts. A total of 1,229 radiomics features were automatically calculated from each aneurysm. The feature number was systematically reduced, and the most important classifying features were selected. A logistic regression model was constructed using the selected features and evaluated on training and test cohorts. Radiomics score (Rad-score) was calculated for each patient and compared between ruptured and unruptured aneurysms.Results: Nine radiomics features were selected from the CTA images and used to build the logistic regression model. The radiomics model has shown good performance in the classification of the aneurysm rupture on training and test cohorts [area under the receiver operating characteristic curve: 0.92 [95% confidence interval CI: 0.89–0.95] and 0.86 [95% CI: 0.80–0.93], respectively, p < 0.001]. Rad-score showed statistically significant differences between ruptured and unruptured aneurysms (median, 2.50 vs. −1.60 and 2.35 vs. −1.01 on training and test cohorts, respectively, p < 0.001).Conclusion: The results indicated the potential of aneurysm radiomics features for automatic classification of aneurysm rupture on CTA images.https://www.frontiersin.org/articles/10.3389/fneur.2021.619864/fullintracranial aneurysmaneurysm rupturesubarachnoid hemorrhagemachine learningradiomics
spellingShingle Osamah Alwalid
Osamah Alwalid
Xi Long
Xi Long
Mingfei Xie
Mingfei Xie
Jiehua Yang
Chunyuan Cen
Chunyuan Cen
Huan Liu
Ping Han
Ping Han
CT Angiography-Based Radiomics for Classification of Intracranial Aneurysm Rupture
Frontiers in Neurology
intracranial aneurysm
aneurysm rupture
subarachnoid hemorrhage
machine learning
radiomics
title CT Angiography-Based Radiomics for Classification of Intracranial Aneurysm Rupture
title_full CT Angiography-Based Radiomics for Classification of Intracranial Aneurysm Rupture
title_fullStr CT Angiography-Based Radiomics for Classification of Intracranial Aneurysm Rupture
title_full_unstemmed CT Angiography-Based Radiomics for Classification of Intracranial Aneurysm Rupture
title_short CT Angiography-Based Radiomics for Classification of Intracranial Aneurysm Rupture
title_sort ct angiography based radiomics for classification of intracranial aneurysm rupture
topic intracranial aneurysm
aneurysm rupture
subarachnoid hemorrhage
machine learning
radiomics
url https://www.frontiersin.org/articles/10.3389/fneur.2021.619864/full
work_keys_str_mv AT osamahalwalid ctangiographybasedradiomicsforclassificationofintracranialaneurysmrupture
AT osamahalwalid ctangiographybasedradiomicsforclassificationofintracranialaneurysmrupture
AT xilong ctangiographybasedradiomicsforclassificationofintracranialaneurysmrupture
AT xilong ctangiographybasedradiomicsforclassificationofintracranialaneurysmrupture
AT mingfeixie ctangiographybasedradiomicsforclassificationofintracranialaneurysmrupture
AT mingfeixie ctangiographybasedradiomicsforclassificationofintracranialaneurysmrupture
AT jiehuayang ctangiographybasedradiomicsforclassificationofintracranialaneurysmrupture
AT chunyuancen ctangiographybasedradiomicsforclassificationofintracranialaneurysmrupture
AT chunyuancen ctangiographybasedradiomicsforclassificationofintracranialaneurysmrupture
AT huanliu ctangiographybasedradiomicsforclassificationofintracranialaneurysmrupture
AT pinghan ctangiographybasedradiomicsforclassificationofintracranialaneurysmrupture
AT pinghan ctangiographybasedradiomicsforclassificationofintracranialaneurysmrupture