TY - JOUR
T1 - Quantitative image signature and machine learning-based prediction of outcomes in cerebral cavernous malformations
T2 - Machine learning for cavernous malformations outcomes
AU - Jabal, Mohamed Sobhi
AU - Mohammed, Marwa A.
AU - Kobeissi, Hassan
AU - Lanzino, Giuseppe
AU - Brinjikji, Waleed
AU - Flemming, Kelly D.
N1 - Publisher Copyright:
© 2023 Elsevier Inc.
PY - 2024/1
Y1 - 2024/1
N2 - Purpose: There is increasing interest in novel prognostic tools and predictive biomarkers to help identify, with more certainty, cerebral cavernous malformations (CCM) susceptible of bleeding if left untreated. We developed explainable quantitative-based machine learning models from magnetic resonance imaging (MRI) in a large CCM cohort to demonstrate the value of artificial intelligence and radiomics in complementing natural history studies for hemorrhage and functional outcome prediction. Materials and Methods: One-hundred-eighty-one patients from a prospectively registered cohort of 366 adults with CCM were included. Fluid attenuated inversion recovery (FLAIR) T2-weighted brain images were preprocessed, and CCM and surrounding edema were segmented before radiomic feature computation. Minority class oversampling, dimensionality reduction and feature selection methods were applied. With prospective hemorrhage as primary outcome, machine learning models were built, cross-validated, and compared using clinico-radiologic, radiomic, and combined features. SHapley Additive exPlanations (SHAP) was used for interpretation to determine the radiomic features with most contribution to hemorrhage prediction. Results: The highest performances in hemorrhage predictions on the test set were combining radiomic and clinico-radiological features with an area under the curve (AUC) of 83% using linear regression and selected features, and an F1 score of 61% and 85% sensitivity using K-nearest neighbors with principal component analysis (PCA). Multilayer perceptron had the best performance predicting modified Rankin Scale ≥ 2 with an AUC of 74% using PCA derived features. For interpretation of the selected radiomic signature XGBoost model, Shapley additive explanations highlighted 6 radiomic features contributing the most to hemorrhage prediction. Conclusion: Quantitative image-based modeling using machine learning has the potential to highlight novel imaging biomarkers that predict hemorrhagic and functional outcomes, ensuring more precise and personalized care for CCM patients.
AB - Purpose: There is increasing interest in novel prognostic tools and predictive biomarkers to help identify, with more certainty, cerebral cavernous malformations (CCM) susceptible of bleeding if left untreated. We developed explainable quantitative-based machine learning models from magnetic resonance imaging (MRI) in a large CCM cohort to demonstrate the value of artificial intelligence and radiomics in complementing natural history studies for hemorrhage and functional outcome prediction. Materials and Methods: One-hundred-eighty-one patients from a prospectively registered cohort of 366 adults with CCM were included. Fluid attenuated inversion recovery (FLAIR) T2-weighted brain images were preprocessed, and CCM and surrounding edema were segmented before radiomic feature computation. Minority class oversampling, dimensionality reduction and feature selection methods were applied. With prospective hemorrhage as primary outcome, machine learning models were built, cross-validated, and compared using clinico-radiologic, radiomic, and combined features. SHapley Additive exPlanations (SHAP) was used for interpretation to determine the radiomic features with most contribution to hemorrhage prediction. Results: The highest performances in hemorrhage predictions on the test set were combining radiomic and clinico-radiological features with an area under the curve (AUC) of 83% using linear regression and selected features, and an F1 score of 61% and 85% sensitivity using K-nearest neighbors with principal component analysis (PCA). Multilayer perceptron had the best performance predicting modified Rankin Scale ≥ 2 with an AUC of 74% using PCA derived features. For interpretation of the selected radiomic signature XGBoost model, Shapley additive explanations highlighted 6 radiomic features contributing the most to hemorrhage prediction. Conclusion: Quantitative image-based modeling using machine learning has the potential to highlight novel imaging biomarkers that predict hemorrhagic and functional outcomes, ensuring more precise and personalized care for CCM patients.
KW - Biomarkers
KW - Cavernous
KW - Machine learning
KW - Malformations
UR - http://www.scopus.com/inward/record.url?scp=85175565678&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85175565678&partnerID=8YFLogxK
U2 - 10.1016/j.jstrokecerebrovasdis.2023.107462
DO - 10.1016/j.jstrokecerebrovasdis.2023.107462
M3 - Article
C2 - 37931483
AN - SCOPUS:85175565678
SN - 1052-3057
VL - 33
JO - Journal of Stroke and Cerebrovascular Diseases
JF - Journal of Stroke and Cerebrovascular Diseases
IS - 1
M1 - 107462
ER -