Intracranial aneurysm instability prediction model based on 4D-Flow MRI and HR-MRI
This study aims to develop a reliable predictive model for assessing intracranial aneurysm (IA) instability by utilizing four-dimensional flow magnetic resonance imaging (4D-Flow MRI) and high-resolution MRI (HR-MRI). Initially, we curated a prospective dataset, dubbed the primary cohort, by aggrega...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Neurotherapeutics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1878747924001922 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832575448859541504 |
|---|---|
| author | Fei Peng Jiaxiang Xia Fandong Zhang Shiyu Lu Hao Wang Jiashu Li Xinmin Liu Yao Zhong Jiahuan Guo Yonghong Duan Binbin Sui Chuyang Ye Yi Ju Shuai Kang Yizhou Yu Xin Feng Xingquan Zhao Rui Li Aihua Liu |
| author_facet | Fei Peng Jiaxiang Xia Fandong Zhang Shiyu Lu Hao Wang Jiashu Li Xinmin Liu Yao Zhong Jiahuan Guo Yonghong Duan Binbin Sui Chuyang Ye Yi Ju Shuai Kang Yizhou Yu Xin Feng Xingquan Zhao Rui Li Aihua Liu |
| author_sort | Fei Peng |
| collection | DOAJ |
| description | This study aims to develop a reliable predictive model for assessing intracranial aneurysm (IA) instability by utilizing four-dimensional flow magnetic resonance imaging (4D-Flow MRI) and high-resolution MRI (HR-MRI). Initially, we curated a prospective dataset, dubbed the primary cohort, by aggregating patient data that was consecutively enrolled across two centers from November 2018 to November 2021. Unstable aneurysms were defined as those with symptoms, morphological change or ruptured during follow-up periods. We introduce a specialized ensemble learning framework, termed the Hybrid Model, which synergistically combines two heterogeneous base learning algorithms: 4D-Flow logistic regression (4D-Flow-LR) and Multi-crop Attention Branch Network (MicroAB-Net). The ability of the hybrid model to predict aneurysm instability was compared with baseline models: PHASES (population, hypertension, age, size, earlier rupture, and site) LR, ELAPSS (earlier subarachnoid hemorrhage, location, age, population, size, and shape) LR, aneurysm wall enhancement (AWE) LR, and Radiomics using the area under the curve (AUC) with Delong's test. Finally, the Hybrid Model was further validated in the validation cohort (patients enrolled between December 2021 to May 2022). In the primary cohort, 189 patients (144 women [76.2 %]; aged 58.90 years ± 10.32) with 213 IAs were included. In the validation cohort, 48 patients (35 women [72.9 %]; aged 55.0 years ± 10.77) with 53 IAs were included. The Hybrid Model achieved the highest performance both in the primary cohort (AUC = 0.854) and the validation cohort (AUC = 0.876). The Hybrid model provided a promising prediction of aneurysm instability. |
| format | Article |
| id | doaj-art-3a18344d5048498490cc504a1e162cb2 |
| institution | Kabale University |
| issn | 1878-7479 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Neurotherapeutics |
| spelling | doaj-art-3a18344d5048498490cc504a1e162cb22025-02-01T04:11:53ZengElsevierNeurotherapeutics1878-74792025-01-01221e00505Intracranial aneurysm instability prediction model based on 4D-Flow MRI and HR-MRIFei Peng0Jiaxiang Xia1Fandong Zhang2Shiyu Lu3Hao Wang4Jiashu Li5Xinmin Liu6Yao Zhong7Jiahuan Guo8Yonghong Duan9Binbin Sui10Chuyang Ye11Yi Ju12Shuai Kang13Yizhou Yu14Xin Feng15Xingquan Zhao16Rui Li17Aihua Liu18Beijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaBeijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDeepwise Artificial Intelligence (AI) Lab, Deepwise Inc., Beijing, ChinaDeepwise Artificial Intelligence (AI) Lab, Deepwise Inc., Beijing, China; School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, ChinaDeepwise Artificial Intelligence (AI) Lab, Deepwise Inc., Beijing, ChinaDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Neurosurgery, The Second Affiliated Hospital, Hengyang Medical School, University of South China, Hengyang, Hunan, ChinaTiantan Neuroimaging Center of Excellence, China National Clinical Research Center for Neurological Diseases, Beijing, ChinaSchool of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, ChinaDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Computer Science, The University of Hong Kong, Hong Kong, ChinaNeurosurgery Center, Department of Cerebrovascular Surgery, Zhujiang Hospital, Southern Medical University, Guangzhou, Guangdong, China; Corresponding authors.Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China; Corresponding authors.Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China; Corresponding authors.Beijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University, Beijing, China; Corresponding authors.This study aims to develop a reliable predictive model for assessing intracranial aneurysm (IA) instability by utilizing four-dimensional flow magnetic resonance imaging (4D-Flow MRI) and high-resolution MRI (HR-MRI). Initially, we curated a prospective dataset, dubbed the primary cohort, by aggregating patient data that was consecutively enrolled across two centers from November 2018 to November 2021. Unstable aneurysms were defined as those with symptoms, morphological change or ruptured during follow-up periods. We introduce a specialized ensemble learning framework, termed the Hybrid Model, which synergistically combines two heterogeneous base learning algorithms: 4D-Flow logistic regression (4D-Flow-LR) and Multi-crop Attention Branch Network (MicroAB-Net). The ability of the hybrid model to predict aneurysm instability was compared with baseline models: PHASES (population, hypertension, age, size, earlier rupture, and site) LR, ELAPSS (earlier subarachnoid hemorrhage, location, age, population, size, and shape) LR, aneurysm wall enhancement (AWE) LR, and Radiomics using the area under the curve (AUC) with Delong's test. Finally, the Hybrid Model was further validated in the validation cohort (patients enrolled between December 2021 to May 2022). In the primary cohort, 189 patients (144 women [76.2 %]; aged 58.90 years ± 10.32) with 213 IAs were included. In the validation cohort, 48 patients (35 women [72.9 %]; aged 55.0 years ± 10.77) with 53 IAs were included. The Hybrid Model achieved the highest performance both in the primary cohort (AUC = 0.854) and the validation cohort (AUC = 0.876). The Hybrid model provided a promising prediction of aneurysm instability.http://www.sciencedirect.com/science/article/pii/S1878747924001922Intracranial aneurysmMRIMachine learningEnsemble learningHemodynamics |
| spellingShingle | Fei Peng Jiaxiang Xia Fandong Zhang Shiyu Lu Hao Wang Jiashu Li Xinmin Liu Yao Zhong Jiahuan Guo Yonghong Duan Binbin Sui Chuyang Ye Yi Ju Shuai Kang Yizhou Yu Xin Feng Xingquan Zhao Rui Li Aihua Liu Intracranial aneurysm instability prediction model based on 4D-Flow MRI and HR-MRI Neurotherapeutics Intracranial aneurysm MRI Machine learning Ensemble learning Hemodynamics |
| title | Intracranial aneurysm instability prediction model based on 4D-Flow MRI and HR-MRI |
| title_full | Intracranial aneurysm instability prediction model based on 4D-Flow MRI and HR-MRI |
| title_fullStr | Intracranial aneurysm instability prediction model based on 4D-Flow MRI and HR-MRI |
| title_full_unstemmed | Intracranial aneurysm instability prediction model based on 4D-Flow MRI and HR-MRI |
| title_short | Intracranial aneurysm instability prediction model based on 4D-Flow MRI and HR-MRI |
| title_sort | intracranial aneurysm instability prediction model based on 4d flow mri and hr mri |
| topic | Intracranial aneurysm MRI Machine learning Ensemble learning Hemodynamics |
| url | http://www.sciencedirect.com/science/article/pii/S1878747924001922 |
| work_keys_str_mv | AT feipeng intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT jiaxiangxia intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT fandongzhang intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT shiyulu intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT haowang intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT jiashuli intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT xinminliu intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT yaozhong intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT jiahuanguo intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT yonghongduan intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT binbinsui intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT chuyangye intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT yiju intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT shuaikang intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT yizhouyu intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT xinfeng intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT xingquanzhao intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT ruili intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri AT aihualiu intracranialaneurysminstabilitypredictionmodelbasedon4dflowmriandhrmri |