Identifying vulnerable plaques: A 3D carotid plaque radiomics model based on HRMRI
BackgroundIdentification of vulnerable carotid plaque is important for the treatment and prevention of stroke. In previous studies, plaque vulnerability was assessed qualitatively. We aimed to develop a 3D carotid plaque radiomics model based on high-resolution magnetic resonance imaging (HRMRI) to...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2023.1050899/full |
| _version_ | 1797942934374449152 |
|---|---|
| author | Xun Zhang Zhaohui Hua Rui Chen Zhouyang Jiao Jintao Shan Chong Li Zhen Li |
| author_facet | Xun Zhang Zhaohui Hua Rui Chen Zhouyang Jiao Jintao Shan Chong Li Zhen Li |
| author_sort | Xun Zhang |
| collection | DOAJ |
| description | BackgroundIdentification of vulnerable carotid plaque is important for the treatment and prevention of stroke. In previous studies, plaque vulnerability was assessed qualitatively. We aimed to develop a 3D carotid plaque radiomics model based on high-resolution magnetic resonance imaging (HRMRI) to quantitatively identify vulnerable plaques.MethodsNinety patients with carotid atherosclerosis who underwent HRMRI were randomized into training and test cohorts. Using the radiological characteristics of carotid plaques, a traditional model was constructed. A 3D carotid plaque radiomics model was constructed using the radiomics features of 3D T1-SPACE and its contrast-enhanced sequences. A combined model was constructed using radiological and radiomics characteristics. Nomogram was generated based on the combined models, and ROC curves were utilized to assess the performance of each model.Results48 patients (53.33%) were symptomatic and 42 (46.67%) were asymptomatic. The traditional model was constructed using intraplaque hemorrhage, plaque enhancement, wall remodeling pattern, and lumen stenosis, and it provided an area under the curve (AUC) of 0.816 vs. 0.778 in the training and testing sets. In the two cohorts, the 3D carotid plaque radiomics model and the combined model had an AUC of 0.915 vs. 0.835 and 0.957 vs. 0.864, respectively. In the training set, both the radiomics model and the combination model outperformed the traditional model, but there was no significant difference between the radiomics model and the combined model.ConclusionsHRMRI-based 3D carotid radiomics models can improve the precision of detecting vulnerable carotid plaques, consequently improving risk classification and clinical decision-making in patients with carotid stenosis. |
| first_indexed | 2024-04-10T20:16:24Z |
| format | Article |
| id | doaj.art-2ff61cc70bd245a985cbaf8f017a5e1a |
| institution | Directory Open Access Journal |
| issn | 1664-2295 |
| language | English |
| last_indexed | 2024-04-10T20:16:24Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj.art-2ff61cc70bd245a985cbaf8f017a5e1a2023-01-26T05:26:46ZengFrontiers Media S.A.Frontiers in Neurology1664-22952023-01-011410.3389/fneur.2023.10508991050899Identifying vulnerable plaques: A 3D carotid plaque radiomics model based on HRMRIXun Zhang0Zhaohui Hua1Rui Chen2Zhouyang Jiao3Jintao Shan4Chong Li5Zhen Li6Department of Endovascular Surgery, First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, ChinaDepartment of Endovascular Surgery, First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, ChinaDepartment of Magnetic Resonance Imaging, First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, ChinaDepartment of Endovascular Surgery, First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, ChinaDepartment of Endovascular Surgery, First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, ChinaDivision of Vascular Surgery, New York University Medical Center, New York, NY, United StatesDepartment of Endovascular Surgery, First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, ChinaBackgroundIdentification of vulnerable carotid plaque is important for the treatment and prevention of stroke. In previous studies, plaque vulnerability was assessed qualitatively. We aimed to develop a 3D carotid plaque radiomics model based on high-resolution magnetic resonance imaging (HRMRI) to quantitatively identify vulnerable plaques.MethodsNinety patients with carotid atherosclerosis who underwent HRMRI were randomized into training and test cohorts. Using the radiological characteristics of carotid plaques, a traditional model was constructed. A 3D carotid plaque radiomics model was constructed using the radiomics features of 3D T1-SPACE and its contrast-enhanced sequences. A combined model was constructed using radiological and radiomics characteristics. Nomogram was generated based on the combined models, and ROC curves were utilized to assess the performance of each model.Results48 patients (53.33%) were symptomatic and 42 (46.67%) were asymptomatic. The traditional model was constructed using intraplaque hemorrhage, plaque enhancement, wall remodeling pattern, and lumen stenosis, and it provided an area under the curve (AUC) of 0.816 vs. 0.778 in the training and testing sets. In the two cohorts, the 3D carotid plaque radiomics model and the combined model had an AUC of 0.915 vs. 0.835 and 0.957 vs. 0.864, respectively. In the training set, both the radiomics model and the combination model outperformed the traditional model, but there was no significant difference between the radiomics model and the combined model.ConclusionsHRMRI-based 3D carotid radiomics models can improve the precision of detecting vulnerable carotid plaques, consequently improving risk classification and clinical decision-making in patients with carotid stenosis.https://www.frontiersin.org/articles/10.3389/fneur.2023.1050899/fullcarotid atherosclerosis (AS)radiomics3D reconstructionvulnerable plaquehigh-resolution magnetic resonance imagingstroke |
| spellingShingle | Xun Zhang Zhaohui Hua Rui Chen Zhouyang Jiao Jintao Shan Chong Li Zhen Li Identifying vulnerable plaques: A 3D carotid plaque radiomics model based on HRMRI Frontiers in Neurology carotid atherosclerosis (AS) radiomics 3D reconstruction vulnerable plaque high-resolution magnetic resonance imaging stroke |
| title | Identifying vulnerable plaques: A 3D carotid plaque radiomics model based on HRMRI |
| title_full | Identifying vulnerable plaques: A 3D carotid plaque radiomics model based on HRMRI |
| title_fullStr | Identifying vulnerable plaques: A 3D carotid plaque radiomics model based on HRMRI |
| title_full_unstemmed | Identifying vulnerable plaques: A 3D carotid plaque radiomics model based on HRMRI |
| title_short | Identifying vulnerable plaques: A 3D carotid plaque radiomics model based on HRMRI |
| title_sort | identifying vulnerable plaques a 3d carotid plaque radiomics model based on hrmri |
| topic | carotid atherosclerosis (AS) radiomics 3D reconstruction vulnerable plaque high-resolution magnetic resonance imaging stroke |
| url | https://www.frontiersin.org/articles/10.3389/fneur.2023.1050899/full |
| work_keys_str_mv | AT xunzhang identifyingvulnerableplaquesa3dcarotidplaqueradiomicsmodelbasedonhrmri AT zhaohuihua identifyingvulnerableplaquesa3dcarotidplaqueradiomicsmodelbasedonhrmri AT ruichen identifyingvulnerableplaquesa3dcarotidplaqueradiomicsmodelbasedonhrmri AT zhouyangjiao identifyingvulnerableplaquesa3dcarotidplaqueradiomicsmodelbasedonhrmri AT jintaoshan identifyingvulnerableplaquesa3dcarotidplaqueradiomicsmodelbasedonhrmri AT chongli identifyingvulnerableplaquesa3dcarotidplaqueradiomicsmodelbasedonhrmri AT zhenli identifyingvulnerableplaquesa3dcarotidplaqueradiomicsmodelbasedonhrmri |