Radiomics-Based Prediction of Collateral Status from CT Angiography of Patients Following a Large Vessel Occlusion Stroke
Background: A major driver of individual variation in long-term outcomes following a large vessel occlusion (LVO) stroke is the degree of collateral arterial circulation. We aimed to develop and evaluate machine-learning models that quantify LVO collateral status using admission computed tomography...
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/14/5/485 |
| _version_ | 1797264663249944576 |
|---|---|
| author | Emily W. Avery Anthony Abou-Karam Sandra Abi-Fadel Jonas Behland Adrian Mak Stefan P. Haider Tal Zeevi Pina C. Sanelli Christopher G. Filippi Ajay Malhotra Charles C. Matouk Guido J. Falcone Nils Petersen Lauren H. Sansing Kevin N. Sheth Seyedmehdi Payabvash |
| author_facet | Emily W. Avery Anthony Abou-Karam Sandra Abi-Fadel Jonas Behland Adrian Mak Stefan P. Haider Tal Zeevi Pina C. Sanelli Christopher G. Filippi Ajay Malhotra Charles C. Matouk Guido J. Falcone Nils Petersen Lauren H. Sansing Kevin N. Sheth Seyedmehdi Payabvash |
| author_sort | Emily W. Avery |
| collection | DOAJ |
| description | Background: A major driver of individual variation in long-term outcomes following a large vessel occlusion (LVO) stroke is the degree of collateral arterial circulation. We aimed to develop and evaluate machine-learning models that quantify LVO collateral status using admission computed tomography angiography (CTA) radiomics. Methods: We extracted 1116 radiomic features from the anterior circulation territories from admission CTAs of 600 patients experiencing an acute LVO stroke. We trained and validated multiple machine-learning models for the prediction of collateral status based on consensus from two neuroradiologists as ground truth. Models were first trained to predict (1) good vs. intermediate or poor, or (2) good vs. intermediate or poor collateral status. Then, model predictions were combined to determine a three-tier collateral score (good, intermediate, or poor). We used the receiver operating characteristics area under the curve (AUC) to evaluate prediction accuracy. Results: We included 499 patients in training and 101 in an independent test cohort. The best-performing models achieved an averaged cross-validation AUC of 0.80 ± 0.05 for poor vs. intermediate/good collateral and 0.69 ± 0.05 for good vs. intermediate/poor, and AUC = 0.77 (0.67–0.87) and AUC = 0.78 (0.70–0.90) in the independent test cohort, respectively. The collateral scores predicted by the radiomics model were correlated with (rho = 0.45, <i>p</i> = 0.002) and were independent predictors of 3-month clinical outcome (<i>p</i> = 0.018) in the independent test cohort. Conclusions: Automated tools for the assessment of collateral status from admission CTA—such as the radiomics models described here—can generate clinically relevant and reproducible collateral scores to facilitate a timely treatment triage in patients experiencing an acute LVO stroke. |
| first_indexed | 2024-04-25T00:32:29Z |
| format | Article |
| id | doaj.art-a9ca0c7c749943ccad13131170b9a977 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-04-25T00:32:29Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-a9ca0c7c749943ccad13131170b9a9772024-03-12T16:41:55ZengMDPI AGDiagnostics2075-44182024-02-0114548510.3390/diagnostics14050485Radiomics-Based Prediction of Collateral Status from CT Angiography of Patients Following a Large Vessel Occlusion StrokeEmily W. Avery0Anthony Abou-Karam1Sandra Abi-Fadel2Jonas Behland3Adrian Mak4Stefan P. Haider5Tal Zeevi6Pina C. Sanelli7Christopher G. Filippi8Ajay Malhotra9Charles C. Matouk10Guido J. Falcone11Nils Petersen12Lauren H. Sansing13Kevin N. Sheth14Seyedmehdi Payabvash15Section of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USASection of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USASection of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USASection of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USASection of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USASection of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USASection of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USASection of Neuroradiology, Department of Radiology, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell Health, Manhasset, NY 11030, USASection of Neuroradiology, Department of Radiology, Tufts School of Medicine, Boston, MA 02111, USASection of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USADivision of Neurovascular Surgery, Department of Neurosurgery, Yale School of Medicine, New Haven, CT 06520, USADivision of Neurocritical Care and Emergency Neurology, Department of Neurology, Yale School of Medicine, New Haven, CT 06520, USADivision of Neurocritical Care and Emergency Neurology, Department of Neurology, Yale School of Medicine, New Haven, CT 06520, USADivision of Stroke and Vascular Neurology, Department of Neurology, Yale School of Medicine, New Haven, CT 06520, USADivision of Neurocritical Care and Emergency Neurology, Department of Neurology, Yale School of Medicine, New Haven, CT 06520, USASection of Neuroradiology, Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT 06520, USABackground: A major driver of individual variation in long-term outcomes following a large vessel occlusion (LVO) stroke is the degree of collateral arterial circulation. We aimed to develop and evaluate machine-learning models that quantify LVO collateral status using admission computed tomography angiography (CTA) radiomics. Methods: We extracted 1116 radiomic features from the anterior circulation territories from admission CTAs of 600 patients experiencing an acute LVO stroke. We trained and validated multiple machine-learning models for the prediction of collateral status based on consensus from two neuroradiologists as ground truth. Models were first trained to predict (1) good vs. intermediate or poor, or (2) good vs. intermediate or poor collateral status. Then, model predictions were combined to determine a three-tier collateral score (good, intermediate, or poor). We used the receiver operating characteristics area under the curve (AUC) to evaluate prediction accuracy. Results: We included 499 patients in training and 101 in an independent test cohort. The best-performing models achieved an averaged cross-validation AUC of 0.80 ± 0.05 for poor vs. intermediate/good collateral and 0.69 ± 0.05 for good vs. intermediate/poor, and AUC = 0.77 (0.67–0.87) and AUC = 0.78 (0.70–0.90) in the independent test cohort, respectively. The collateral scores predicted by the radiomics model were correlated with (rho = 0.45, <i>p</i> = 0.002) and were independent predictors of 3-month clinical outcome (<i>p</i> = 0.018) in the independent test cohort. Conclusions: Automated tools for the assessment of collateral status from admission CTA—such as the radiomics models described here—can generate clinically relevant and reproducible collateral scores to facilitate a timely treatment triage in patients experiencing an acute LVO stroke.https://www.mdpi.com/2075-4418/14/5/485strokelarge vessel occlusionradiomicsmachine learningcollateral status |
| spellingShingle | Emily W. Avery Anthony Abou-Karam Sandra Abi-Fadel Jonas Behland Adrian Mak Stefan P. Haider Tal Zeevi Pina C. Sanelli Christopher G. Filippi Ajay Malhotra Charles C. Matouk Guido J. Falcone Nils Petersen Lauren H. Sansing Kevin N. Sheth Seyedmehdi Payabvash Radiomics-Based Prediction of Collateral Status from CT Angiography of Patients Following a Large Vessel Occlusion Stroke Diagnostics stroke large vessel occlusion radiomics machine learning collateral status |
| title | Radiomics-Based Prediction of Collateral Status from CT Angiography of Patients Following a Large Vessel Occlusion Stroke |
| title_full | Radiomics-Based Prediction of Collateral Status from CT Angiography of Patients Following a Large Vessel Occlusion Stroke |
| title_fullStr | Radiomics-Based Prediction of Collateral Status from CT Angiography of Patients Following a Large Vessel Occlusion Stroke |
| title_full_unstemmed | Radiomics-Based Prediction of Collateral Status from CT Angiography of Patients Following a Large Vessel Occlusion Stroke |
| title_short | Radiomics-Based Prediction of Collateral Status from CT Angiography of Patients Following a Large Vessel Occlusion Stroke |
| title_sort | radiomics based prediction of collateral status from ct angiography of patients following a large vessel occlusion stroke |
| topic | stroke large vessel occlusion radiomics machine learning collateral status |
| url | https://www.mdpi.com/2075-4418/14/5/485 |
| work_keys_str_mv | AT emilywavery radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke AT anthonyaboukaram radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke AT sandraabifadel radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke AT jonasbehland radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke AT adrianmak radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke AT stefanphaider radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke AT talzeevi radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke AT pinacsanelli radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke AT christophergfilippi radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke AT ajaymalhotra radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke AT charlescmatouk radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke AT guidojfalcone radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke AT nilspetersen radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke AT laurenhsansing radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke AT kevinnsheth radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke AT seyedmehdipayabvash radiomicsbasedpredictionofcollateralstatusfromctangiographyofpatientsfollowingalargevesselocclusionstroke |