1
|
Jiang J, Wei J, Zhu Y, Wei L, Wei X, Tian H, Zhang L, Wang T, Cheng Y, Zhao Q, Sun Z, Du H, Huang Y, Liu H, Li Y. Clot-based radiomics model for cardioembolic stroke prediction with CT imaging before recanalization: a multicenter study. Eur Radiol 2023; 33:970-980. [PMID: 36066731 DOI: 10.1007/s00330-022-09116-4] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2022] [Revised: 07/11/2022] [Accepted: 08/12/2022] [Indexed: 02/03/2023]
Abstract
OBJECTIVES To develop a clot-based radiomics model using CT imaging radiomic features and machine learning to identify cardioembolic (CE) stroke before mechanical thrombectomy (MTB) in patients with acute ischemic stroke (AIS). MATERIALS AND METHODS This retrospective four-center study consecutively included 403 patients with AIS who sequentially underwent CT and MTB between April 2016 and July 2021. These were grouped into training, testing, and external validation cohorts. Thrombus-extracted radiomic features and basic information were gathered to construct a machine learning model to predict CE stroke. The radiological characteristics and basic information were used to build a routine radiological model. A combined radiomics and radiological features model was also developed. The performances of all models were evaluated and compared in the validation cohort. A histological analysis helped further assess the proposed model in all patients. RESULTS The radiomics model yielded an area under the curve (AUC) of 0.838 (95% confidence interval [CI], 0.771-0.891) for predicting CE stroke in the validation cohort, significantly higher than the radiological model (AUC, 0.713; 95% CI, 0.636-0.781; p = 0.007) but similar to the combined model (AUC, 0.855; 95% CI, 0.791-0.906; p = 0.14). The thrombus radiomic features achieved stronger correlations with red blood cells (|rmax|, 0.74 vs. 0.32) and fibrin and platelet (|rmax|, 0.68 vs. 0.18) than radiological characteristics. CONCLUSION The proposed CT-based radiomics model could reliably predict CE stroke in AIS, performing better than the routine radiological method. KEY POINTS • Admission CT imaging could offer valuable information to identify the acute ischemic stroke source by radiomics analysis. • The proposed CT imaging-based radiomics model yielded a higher area under the curve (0.838) than the routine radiological method (0.713; p = 0.007). • Several radiomic features showed significantly stronger correlations with two main thrombus constituents (red blood cells, |rmax|, 0.74; fibrin and platelet, |rmax|, 0.68) than routine radiological characteristics.
Collapse
Affiliation(s)
- Jingxuan Jiang
- Institute of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, No. 600 Yishan Road, Shanghai, 200233, China.,Department of Radiology, Affiliated Hospital of Nantong University, Nantong, 226001, China
| | - Jianyong Wei
- Clinical Research Center, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai, 200233, China
| | - Yueqi Zhu
- Institute of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, No. 600 Yishan Road, Shanghai, 200233, China
| | - Liming Wei
- Institute of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, No. 600 Yishan Road, Shanghai, 200233, China
| | - Xiaoer Wei
- Institute of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, No. 600 Yishan Road, Shanghai, 200233, China
| | - Hao Tian
- Department of Radiology, Affiliated Hospital of Nantong University, Nantong, 226001, China
| | - Lei Zhang
- Department of Radiology, Wuxi Second People's Hospital, Wuxi, 214000, China
| | - Tianle Wang
- Department of Radiology, Affiliated No. 1 People's Hospital of Nantong University, Nantong, 226001, China
| | - Yue Cheng
- Department of Radiology, Wuxi Second People's Hospital, Wuxi, 214000, China
| | - Qianqian Zhao
- Institute of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, No. 600 Yishan Road, Shanghai, 200233, China
| | - Zheng Sun
- Institute of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, No. 600 Yishan Road, Shanghai, 200233, China
| | - Haiyan Du
- Institute of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, No. 600 Yishan Road, Shanghai, 200233, China
| | - Yu Huang
- Institute of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, No. 600 Yishan Road, Shanghai, 200233, China
| | - Hui Liu
- Institute of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, No. 600 Yishan Road, Shanghai, 200233, China
| | - Yuehua Li
- Institute of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, No. 600 Yishan Road, Shanghai, 200233, China.
| |
Collapse
|
3
|
Klinger-Gratz PP, Schroth G, Gralla J, Jung S, Weisstanner C, Verma RK, Mordasini P, Kellner-Weldon F, Hsieh K, Heldner MR, Fischer U, Arnold M, Mattle HP, El-Koussy M. Protected stent retriever thrombectomy prevents iatrogenic emboli in new vascular territories. Neuroradiology 2015; 57:1045-54. [PMID: 26319999 PMCID: PMC4602059 DOI: 10.1007/s00234-015-1583-8] [Citation(s) in RCA: 36] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2015] [Accepted: 08/19/2015] [Indexed: 01/19/2023]
Abstract
Introduction Diagnostic tools to show emboli reliably and protection techniques against embolization when employing stent retrievers are necessary to improve endovascular stroke therapy. The aim of the present study was to investigate iatrogenic emboli using susceptibility-weighted imaging (SWI) in an open series of patients who had been treated with stent retriever thrombectomy using emboli protection techniques. Methods Patients with anterior circulation stroke examined with MRI before and after stent retriever thrombectomy were assessed for iatrogenic embolic events. Thrombectomy was performed in flow arrest and under aspiration using a balloon-mounted guiding catheter, a distal access catheter, or both. Results In 13 of 57 patients (22.8 %) post-interventional SWI sequences detected 16 microemboli. Three of them were associated with small ischemic lesions on diffusion-weighted imaging (DWI). None of the microemboli were located in a new vascular territory, none showed clinical signs, and all 13 patients have been rated as Thrombolysis in Cerebral Infarction (TICI) 2b (n = 3) or 3 (n = 10). Retrospective reevaluation of the digital subtraction angiography (DSA) detected discrete flow stagnation nearby the iatrogenic microemboli in four patients with a positive persistent collateral sign in one. Conclusion Our study demonstrates two things: First, SWI seems to be more sensitive to detect emboli than DWI and DSA and, second, proximal or distal protected stent retriever thrombectomy seems to prevent iatrogenic embolization into new vascular territories during retraction of the thrombus, but not downstream during mobilization of the thrombus. Both techniques should be investigated and refined further.
Collapse
Affiliation(s)
- Pascal P Klinger-Gratz
- Department of Diagnostic and Interventional Neuroradiology, Inselspital, Freiburgstrasse 10, Bern University Hospital and University of Bern, 3010, Bern, Switzerland.,Department of Radiology, University of Basel, Basel, Switzerland
| | - Gerhard Schroth
- Department of Diagnostic and Interventional Neuroradiology, Inselspital, Freiburgstrasse 10, Bern University Hospital and University of Bern, 3010, Bern, Switzerland.
| | - Jan Gralla
- Department of Diagnostic and Interventional Neuroradiology, Inselspital, Freiburgstrasse 10, Bern University Hospital and University of Bern, 3010, Bern, Switzerland
| | - Simon Jung
- Department of Diagnostic and Interventional Neuroradiology, Inselspital, Freiburgstrasse 10, Bern University Hospital and University of Bern, 3010, Bern, Switzerland.,Department of Neurology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland
| | - Christian Weisstanner
- Department of Diagnostic and Interventional Neuroradiology, Inselspital, Freiburgstrasse 10, Bern University Hospital and University of Bern, 3010, Bern, Switzerland
| | - Rajeev K Verma
- Department of Diagnostic and Interventional Neuroradiology, Inselspital, Freiburgstrasse 10, Bern University Hospital and University of Bern, 3010, Bern, Switzerland
| | - Pasquale Mordasini
- Department of Diagnostic and Interventional Neuroradiology, Inselspital, Freiburgstrasse 10, Bern University Hospital and University of Bern, 3010, Bern, Switzerland
| | - Frauke Kellner-Weldon
- Department of Diagnostic and Interventional Neuroradiology, Inselspital, Freiburgstrasse 10, Bern University Hospital and University of Bern, 3010, Bern, Switzerland
| | - Kety Hsieh
- Department of Diagnostic and Interventional Neuroradiology, Inselspital, Freiburgstrasse 10, Bern University Hospital and University of Bern, 3010, Bern, Switzerland
| | - Mirjam R Heldner
- Department of Neurology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland
| | - Urs Fischer
- Department of Neurology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland
| | - Marcel Arnold
- Department of Neurology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland
| | - Heinrich P Mattle
- Department of Neurology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland
| | - Marwan El-Koussy
- Department of Diagnostic and Interventional Neuroradiology, Inselspital, Freiburgstrasse 10, Bern University Hospital and University of Bern, 3010, Bern, Switzerland
| |
Collapse
|
4
|
Endovascular Treatment of Acute Stroke: Evolution and Selection of Techniques and Instruments Based on Thrombus Imaging. Clin Neuroradiol 2015. [PMID: 26216652 DOI: 10.1007/s00062-015-0435-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
Abstract
Mechanical thrombectomy provides higher recanalization rates than intravenous or intra-arterial thrombolysis. Finally this has been shown to translate into improved clinical outcome in six multicentric randomized controlled trials. However, within cohorts the clinical outcomes may vary, depending on the endovascular techniques applied. Systems aiming mainly for thrombus fragmentation and lacking a protection against distal embolization have shown disappointing results when compared to recent stent-retriever studies or even to historical data on local arterial fibrinolysis. Procedure-related embolic events are usually graded as adverse events in interventional neuroradiology. In stroke, however, the clinical consequences of secondary emboli have so far mostly been neglected and attributed to progression of the stroke itself. We summarize the evolution of instruments and techniques for endovascular, image-guided, microneurosurgical recanalization in acute stroke, and discuss how to avoid procedure-related embolic complications.
Collapse
|