Z Shi1, G Z Chen2, L Mao3, X L Li3, C S Zhou1, S Xia4, Y X Zhang5, B Zhang6, B Hu1, G M Lu1, L J Zhang7. 1. From the Department of Diagnostic Radiology (Z.S., C.S.Z., B.H., G.M.L., L.J.Z.), Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu, China. 2. Department of Medical Imaging (G.Z.C.), Nanjing First Hospital, Nanjing, Jiangsu, China. 3. Deepwise AI Lab (L.M., X.L.L.), Beijing, China. 4. Department of Radiology (S.X.), Tianjin First Central Hospital, Tianjin, China. 5. Laboratory of Image Science and Technology (Y.X.Z.), School of Computer Science and Engineering, Southeast University, Nanjing, China. 6. Department of Radiology (B.Z.), Taizhou People's Hospital, Taizhou, Jiangsu, China. 7. From the Department of Diagnostic Radiology (Z.S., C.S.Z., B.H., G.M.L., L.J.Z.), Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu, China kevinzhlj@163.com.
Abstract
BACKGROUND AND PURPOSE: Small intracranial aneurysms are being increasingly detected while the rupture risk is not well-understood. We aimed to develop rupture-risk models of small aneurysms by combining clinical, morphologic, and hemodynamic information based on machine learning techniques and to test the models in external validation datasets. MATERIALS AND METHODS: From January 2010 to December 2016, five hundred four consecutive patients with only small aneurysms (<5 mm) detected by CTA and invasive cerebral angiography (or surgery) were retrospectively enrolled and randomly split into training (81%) and internal validation (19%) sets to derive and validate the proposed machine learning models (support vector machine, random forest, logistic regression, and multilayer perceptron). Hemodynamic parameters were obtained using computational fluid dynamics simulation. External validation was performed in other hospitals to test the models. RESULTS: The support vector machine performed the best with areas under the curve of 0.88 (95% CI, 0.85-0.92) and 0.91 (95% CI, 0.74-0.98) in the training and internal validation datasets, respectively. Feature ranks suggested hemodynamic parameters, including stable flow pattern, concentrated inflow streams, and a small (<50%) flow-impingement zone, and the oscillatory shear index coefficient of variation, were the best predictors of aneurysm rupture. The support vector machine showed an area under the curve of 0.82 (95% CI, 0.69-0.94) in the external validation dataset, and no significant difference was found for the areas under the curve between internal and external validation datasets (P = .21). CONCLUSIONS: This study revealed that machine learning had a good performance in predicting the rupture status of small aneurysms in both internal and external datasets. Aneurysm hemodynamic parameters were regarded as the most important predictors.
BACKGROUND AND PURPOSE: Small intracranial aneurysms are being increasingly detected while the rupture risk is not well-understood. We aimed to develop rupture-risk models of small aneurysms by combining clinical, morphologic, and hemodynamic information based on machine learning techniques and to test the models in external validation datasets. MATERIALS AND METHODS: From January 2010 to December 2016, five hundred four consecutive patients with only small aneurysms (<5 mm) detected by CTA and invasive cerebral angiography (or surgery) were retrospectively enrolled and randomly split into training (81%) and internal validation (19%) sets to derive and validate the proposed machine learning models (support vector machine, random forest, logistic regression, and multilayer perceptron). Hemodynamic parameters were obtained using computational fluid dynamics simulation. External validation was performed in other hospitals to test the models. RESULTS: The support vector machine performed the best with areas under the curve of 0.88 (95% CI, 0.85-0.92) and 0.91 (95% CI, 0.74-0.98) in the training and internal validation datasets, respectively. Feature ranks suggested hemodynamic parameters, including stable flow pattern, concentrated inflow streams, and a small (<50%) flow-impingement zone, and the oscillatory shear index coefficient of variation, were the best predictors of aneurysm rupture. The support vector machine showed an area under the curve of 0.82 (95% CI, 0.69-0.94) in the external validation dataset, and no significant difference was found for the areas under the curve between internal and external validation datasets (P = .21). CONCLUSIONS: This study revealed that machine learning had a good performance in predicting the rupture status of small aneurysms in both internal and external datasets. Aneurysm hemodynamic parameters were regarded as the most important predictors.