Radiomics for prediction of intracerebral hemorrhage outcomes: A retrospective multicenter study
Background: Accurate risk stratification of patients with intracerebral hemorrhage (ICH) could help refine adjuvant therapy selection and better understand the clinical course. We aimed to evaluate the value of radiomics features from hematomal and perihematomal edema areas for prognosis prediction...
Main Authors: | , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-01-01
|
Series: | NeuroImage: Clinical |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2213158222003072 |
_version_ | 1797990880934625280 |
---|---|
author | Xiaoyu Huang Dan Wang Qiaoying Zhang Yaqiong Ma Hui Zhao Shenglin Li Juan Deng Jialiang Ren Jingjing Yang Zhiyong Zhao Min Xu Qing Zhou Junlin Zhou |
author_facet | Xiaoyu Huang Dan Wang Qiaoying Zhang Yaqiong Ma Hui Zhao Shenglin Li Juan Deng Jialiang Ren Jingjing Yang Zhiyong Zhao Min Xu Qing Zhou Junlin Zhou |
author_sort | Xiaoyu Huang |
collection | DOAJ |
description | Background: Accurate risk stratification of patients with intracerebral hemorrhage (ICH) could help refine adjuvant therapy selection and better understand the clinical course. We aimed to evaluate the value of radiomics features from hematomal and perihematomal edema areas for prognosis prediction and to develop a model combining clinical and radiomic features for accurate outcome prediction of patients with ICH. Methods: This multicenter study enrolled patients with ICH from January 2016 to November 2021. Their outcomes at 3 months were recorded based on the modified Rankin Scale (good, 0–3; poor, 4–6). Independent clinical and radiomic risk factors for poor outcome were identified through multivariate logistic regression analysis, and predictive models were developed. Model performance and clinical utility were evaluated in both internal and external cohorts. Results: Among the 1098 ICH patients evaluated (mean age, 60 ± 13 years), 703 (64 %) had poor outcomes. Age, hemorrhage volume and location, and Glasgow Coma Scale (GCS) were independently associated with outcomes. The area under the receiver operating characteristic curve (AUC) of the clinical model was 0.881 in the external validation cohort. Addition of the Rad-score (combined hematoma and perihematomal edema area) improved predictive accuracy and model performance (AUC, 0.893), net reclassification improvement, 0.140 (P < 0.001), and integrated discrimination improvement, 0.050 (P < 0.001). Conclusions: The radiomics features of hematomal and perihematomal edema area have additional value in prognostic prediction; moreover, addition of radiomic features significantly improves model accuracy. |
first_indexed | 2024-04-11T08:43:35Z |
format | Article |
id | doaj.art-d46380f96faf4923902d164eb5d0571f |
institution | Directory Open Access Journal |
issn | 2213-1582 |
language | English |
last_indexed | 2024-04-11T08:43:35Z |
publishDate | 2022-01-01 |
publisher | Elsevier |
record_format | Article |
series | NeuroImage: Clinical |
spelling | doaj.art-d46380f96faf4923902d164eb5d0571f2022-12-22T04:34:02ZengElsevierNeuroImage: Clinical2213-15822022-01-0136103242Radiomics for prediction of intracerebral hemorrhage outcomes: A retrospective multicenter studyXiaoyu Huang0Dan Wang1Qiaoying Zhang2Yaqiong Ma3Hui Zhao4Shenglin Li5Juan Deng6Jialiang Ren7Jingjing Yang8Zhiyong Zhao9Min Xu10Qing Zhou11Junlin Zhou12Department of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Second Clinical School, Lanzhou University, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, ChinaDepartment of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, ChinaDepartment of Radiology, Xi’an Central Hospital, Xi An 710000, ChinaSecond Clinical School, Lanzhou University, Lanzhou 730030, China; Department of Radiology, Gansu Provincial Hospital, Lanzhou 730030, ChinaDepartment of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Second Clinical School, Lanzhou University, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, ChinaDepartment of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Second Clinical School, Lanzhou University, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, ChinaDepartment of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Second Clinical School, Lanzhou University, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, ChinaGE Healthcare, Beijing 100176, ChinaDepartment of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Second Clinical School, Lanzhou University, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, ChinaDepartment of Radiology, Gansu Provincial Hospital, Lanzhou 730030, ChinaDepartment of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Second Clinical School, Lanzhou University, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, ChinaDepartment of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Second Clinical School, Lanzhou University, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, ChinaDepartment of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China; Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China; Gansu International Scientific and Technological Cooperation Base of Medical Imaging Artificial Intelligence, Lanzhou 730030, China; Department of Neurosurgery, Lanzhou University Second Hospital Lanzhou 730030, China; Corresponding author at: Department of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China.Background: Accurate risk stratification of patients with intracerebral hemorrhage (ICH) could help refine adjuvant therapy selection and better understand the clinical course. We aimed to evaluate the value of radiomics features from hematomal and perihematomal edema areas for prognosis prediction and to develop a model combining clinical and radiomic features for accurate outcome prediction of patients with ICH. Methods: This multicenter study enrolled patients with ICH from January 2016 to November 2021. Their outcomes at 3 months were recorded based on the modified Rankin Scale (good, 0–3; poor, 4–6). Independent clinical and radiomic risk factors for poor outcome were identified through multivariate logistic regression analysis, and predictive models were developed. Model performance and clinical utility were evaluated in both internal and external cohorts. Results: Among the 1098 ICH patients evaluated (mean age, 60 ± 13 years), 703 (64 %) had poor outcomes. Age, hemorrhage volume and location, and Glasgow Coma Scale (GCS) were independently associated with outcomes. The area under the receiver operating characteristic curve (AUC) of the clinical model was 0.881 in the external validation cohort. Addition of the Rad-score (combined hematoma and perihematomal edema area) improved predictive accuracy and model performance (AUC, 0.893), net reclassification improvement, 0.140 (P < 0.001), and integrated discrimination improvement, 0.050 (P < 0.001). Conclusions: The radiomics features of hematomal and perihematomal edema area have additional value in prognostic prediction; moreover, addition of radiomic features significantly improves model accuracy.http://www.sciencedirect.com/science/article/pii/S2213158222003072Intracerebral hemorrhageRadiomicsNon-contrast computed tomographyPerihematomal edemaOutcome |
spellingShingle | Xiaoyu Huang Dan Wang Qiaoying Zhang Yaqiong Ma Hui Zhao Shenglin Li Juan Deng Jialiang Ren Jingjing Yang Zhiyong Zhao Min Xu Qing Zhou Junlin Zhou Radiomics for prediction of intracerebral hemorrhage outcomes: A retrospective multicenter study NeuroImage: Clinical Intracerebral hemorrhage Radiomics Non-contrast computed tomography Perihematomal edema Outcome |
title | Radiomics for prediction of intracerebral hemorrhage outcomes: A retrospective multicenter study |
title_full | Radiomics for prediction of intracerebral hemorrhage outcomes: A retrospective multicenter study |
title_fullStr | Radiomics for prediction of intracerebral hemorrhage outcomes: A retrospective multicenter study |
title_full_unstemmed | Radiomics for prediction of intracerebral hemorrhage outcomes: A retrospective multicenter study |
title_short | Radiomics for prediction of intracerebral hemorrhage outcomes: A retrospective multicenter study |
title_sort | radiomics for prediction of intracerebral hemorrhage outcomes a retrospective multicenter study |
topic | Intracerebral hemorrhage Radiomics Non-contrast computed tomography Perihematomal edema Outcome |
url | http://www.sciencedirect.com/science/article/pii/S2213158222003072 |
work_keys_str_mv | AT xiaoyuhuang radiomicsforpredictionofintracerebralhemorrhageoutcomesaretrospectivemulticenterstudy AT danwang radiomicsforpredictionofintracerebralhemorrhageoutcomesaretrospectivemulticenterstudy AT qiaoyingzhang radiomicsforpredictionofintracerebralhemorrhageoutcomesaretrospectivemulticenterstudy AT yaqiongma radiomicsforpredictionofintracerebralhemorrhageoutcomesaretrospectivemulticenterstudy AT huizhao radiomicsforpredictionofintracerebralhemorrhageoutcomesaretrospectivemulticenterstudy AT shenglinli radiomicsforpredictionofintracerebralhemorrhageoutcomesaretrospectivemulticenterstudy AT juandeng radiomicsforpredictionofintracerebralhemorrhageoutcomesaretrospectivemulticenterstudy AT jialiangren radiomicsforpredictionofintracerebralhemorrhageoutcomesaretrospectivemulticenterstudy AT jingjingyang radiomicsforpredictionofintracerebralhemorrhageoutcomesaretrospectivemulticenterstudy AT zhiyongzhao radiomicsforpredictionofintracerebralhemorrhageoutcomesaretrospectivemulticenterstudy AT minxu radiomicsforpredictionofintracerebralhemorrhageoutcomesaretrospectivemulticenterstudy AT qingzhou radiomicsforpredictionofintracerebralhemorrhageoutcomesaretrospectivemulticenterstudy AT junlinzhou radiomicsforpredictionofintracerebralhemorrhageoutcomesaretrospectivemulticenterstudy |