Machine Learning Classification of Cerebral Aneurysm Rupture Status with Morphologic Variables and Hemodynamic Parameters.
Ontology highlight
ABSTRACT: Purpose
To construct a classification model of rupture status and to clarify the importance of morphologic variables and hemodynamic parameters on rupture status by applying a machine learning (ML) algorithm to morphologic and hemodynamic data of cerebral aneurysms.Materials and methods
Between 2011 and 2019, 226 (112 ruptured and 114 unruptured) cerebral aneurysms in 188 consecutive patients were retrospectively analyzed with computational fluid dynamics (CFD). A random forest ML algorithm was applied to the results to create three classification models consisting of only morphologic variables (model 1), only hemodynamic parameters (model 2), and both morphologic variables and hemodynamic parameters (model 3). The accuracy of rupture status classification and the importance of each variable or parameter in the models were computed.Results
The accuracy was 77.0% in model 1, 71.2% in model 2, and 78.3% in model 3. The three most important features were projection ratio, size ratio, and aspect ratio in model 1; low shear area ratio, oscillatory shear index, and oscillatory velocity index in model 2; and projection ratio, irregular shape, and size ratio in model 3.Conclusion
Classification models of rupture status of cerebral aneurysms were constructed by applying an ML algorithm to morphologic variables and hemodynamic parameters. The model worked with relatively high accuracy, in which projection ratio, irregular shape, and size ratio were important for the discrimination of ruptured aneurysms.Supplemental material is available for this article.© RSNA, 2020.
SUBMITTER: Tanioka S
PROVIDER: S-EPMC8017392 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The objective of this work is to develop a robust method for human abdominal aortic aneurysm (AAA) centerline detection that can contribute to the accurate computation of features for the prediction of AAA rupture risk. A semiautomatic algorithm is proposed for detecting the lumen centerline in contrast-enhanced abdominal computed tomography images based on online adaboost classifiers, which does not require prior image segmentation. The algorithm was developed and applied to thirty ruptured and thirty unruptured AAA image data sets and the tortuosities of the detected centerline were measured to assess the correlation between AAA tortuosity and the binary ruptured and unruptured labels. The lumen of each data set was segmented manually by a trained radiologist and the resulting centerlines of each data set were defined as the gold standard to evaluate the accuracy of the algorithm and to compare it against two widely used segmentation techniques. The average mean relative accuracy of the offline adaboost classifier is 91.9% with a standard deviation of 1.6%; for the online adaboost classifier it is 93.6% with a standard deviation of 1.9% (p<0.05). The online adaboost classifier outperforms the offline adaboost classifier while their computational costs are similar. Aneurysm tortuosity computed from an accurately derived lumen centerline using online adaboost is statistically higher for ruptured aneurysms compared to unruptured aneurysms, indicating that tortuosity can be used to assess rupture risk in the vascular clinic.
| S-EPMC3776471 | biostudies-literature
Project description:Background: Assessment of cerebral aneurysm rupture risk is an important task, but it remains challenging. Recent works applying machine learning to rupture risk evaluation presented positive results. Yet they were based on limited aspects of data, and lack of interpretability may limit their use in clinical setting. We aimed to develop interpretable machine learning models on multidimensional data for aneurysm rupture risk assessment. Methods: Three hundred seventy-four aneurysms were included in the study. Demographic, medical history, lifestyle behaviors, lipid profile, and morphologies were collected for each patient. Prediction models were derived using machine learning methods (support vector machine, artificial neural network, and XGBoost) and conventional logistic regression. The derived models were compared with the PHASES score method. The Shapley Additive Explanations (SHAP) analysis was applied to improve the interpretability of the best machine learning model and reveal the reasoning behind the predictions made by the model. Results: The best machine learning model (XGBoost) achieved an area under the receiver operating characteristic curve of 0.882 [95% confidence interval (CI) = 0.838-0.927], significantly better than the logistic regression model (0.779; 95% CI = 0.729-0.829; P = 0.002) and the PHASES score method (0.758; 95% CI = 0.713-0.800; P = 0.001). Location, size ratio, and triglyceride level were the three most important features in predicting rupture. Two typical cases were analyzed to demonstrate the interpretability of the model. Conclusions: This study demonstrated the potential of using machine learning for aneurysm rupture risk assessment. Machine learning models performed better than conventional statistical model and the PHASES score method. The SHAP analysis can improve the interpretability of machine learning models and facilitate their use in a clinical setting.
| S-EPMC7785850 | biostudies-literature
Project description:Intracranial aneurysm growth is a significant risk factor for rupture; however, a few aneurysms remain unruptured for long periods, even after growth. Here, we identified hemodynamic features associated with aneurysmal rupture after growth. We analyzed nine middle cerebral artery aneurysms that grew during the follow-up period using computational fluid dynamics analysis. Growth patterns of the middle cerebral artery aneurysms were divided into homothetic growth (Type 1), de novo bleb formation (Type 2), and bleb enlargement (Type 3). Hemodynamic parameters of the four ruptured aneurysms after growth were compared with those of the five unruptured aneurysms. Among nine aneurysms (78%), seven were Type 1, one was Type 2, and one was Type 3. Three (43%) Type 1 aneurysms ruptured after growth. Maximum oscillatory shear index after aneurysmal growth was significantly higher in ruptured Type 1 cases than in unruptured Type 1 cases (ruptured vs. unruptured: 0.455 ± 0.007 vs. 0.319 ± 0.042, p = 0.003). In Type 1 cases, a newly emerged high-oscillatory shear index area was frequently associated with rupture, indicating a rupture point. Aneurysm growth was observed in the direction of the high-pressure difference area before enlargement. In Types 2 and 3 aneurysms, the maximum oscillatory shear index decreased slightly, however, the pressure difference values remain unchanged. In Type 3 aneruysm, the maximum OSI and PD values remained unchanged. This study suggests that hemodynamic variations and growth pattern changes are crucial in rupture risk determination using computational fluid dynamics analysis. High-pressure difference areas may predict aneurysm enlargement direction. Additionally, high maximum oscillatory shear index values after enlargement in cases with homothetic growth patterns were potential rupture risk factors.
| S-EPMC11340937 | biostudies-literature
Project description:The growth of cerebral aneurysms is linked to local hemodynamic conditions, but the driving mechanisms of the growth are poorly understood. The goal of this study was to examine the association between intraaneurysmal hemodynamic features and areas of aneurysm growth, to present the key hemodynamic parameters essential for an accurate prediction of the growth, and to gain a deeper understanding of the underlying mechanisms. Patient-specific images of a growing cerebral aneurysm in 3 different growth stages acquired over a period of 40 months were segmented and reconstructed. A unique aspect of this patient-specific case study was that while one side of the aneurysm stayed stable, the other side continued to grow. This unique case enabled the authors to examine their aims in the same patient with parent and daughter arteries under the same inlet flow conditions. Pulsatile flow in the aneurysm models was simulated using computational fluid dynamics and was validated with in vitro experiments using particle image velocimetry measurements. The authors' detailed analysis of intrasaccular hemodynamics linked the growing regions of aneurysms to flow instabilities and complex vortex structures. Extremely low velocities were observed at or around the center of the unstable vortex structure, which matched well with the growing regions of the studied cerebral aneurysm. Furthermore, the authors observed that the aneurysm wall regions with a growth greater than 0.5 mm coincided with wall regions of lower (< 0.5 Pa) time-averaged wall shear stress (TAWSS), lower instantaneous (< 0.5 Pa) wall shear stress (WSS), and high (> 0.1) oscillatory shear index (OSI). To determine which set of parameters can best identify growing and nongrowing aneurysms, the authors performed statistical analysis for consecutive stages of the growing CA. The results demonstrated that the combination of TAWSS and the distance from the center of the vortical structure has the highest sensitivity and positive predictive value, and relatively high specificity and negative predictive value. These findings suggest that an unstable, recirculating flow structure within the aneurysm sac created in the region adjacent to the aneurysm wall with low TAWSS may be introduced as an accurate criterion to explain the hemodynamic conditions predisposing the aneurysm to growth. The authors' findings are based on one patient's data set, but the study lays out the justification for future large-scale verification. The authors' findings can assist clinicians in differentiating stable and growing aneurysms during preinterventional planning.
| S-EPMC7605304 | biostudies-literature
Project description:Background: Intracranial aneurysm rupture is a devastating medical event with a high morbidity and mortality rate. Thus, timely detection and management are critical. The present study aimed to identify the aneurysm radiomics features associated with rupture and to build and evaluate a radiomics classification model of aneurysm rupture. Methods: Radiomics analysis was applied to CT angiography (CTA) images of 393 patients [152 (38.7%) with ruptured aneurysms]. Patients were divided at a ratio of 7:3 into retrospective training (n = 274) and prospective test (n = 119) cohorts. A total of 1,229 radiomics features were automatically calculated from each aneurysm. The feature number was systematically reduced, and the most important classifying features were selected. A logistic regression model was constructed using the selected features and evaluated on training and test cohorts. Radiomics score (Rad-score) was calculated for each patient and compared between ruptured and unruptured aneurysms. Results: Nine radiomics features were selected from the CTA images and used to build the logistic regression model. The radiomics model has shown good performance in the classification of the aneurysm rupture on training and test cohorts [area under the receiver operating characteristic curve: 0.92 [95% confidence interval CI: 0.89-0.95] and 0.86 [95% CI: 0.80-0.93], respectively, p < 0.001]. Rad-score showed statistically significant differences between ruptured and unruptured aneurysms (median, 2.50 vs. -1.60 and 2.35 vs. -1.01 on training and test cohorts, respectively, p < 0.001). Conclusion: The results indicated the potential of aneurysm radiomics features for automatic classification of aneurysm rupture on CTA images.
| S-EPMC7937935 | biostudies-literature
Project description:Background and purposeComparisons of geometric data of ruptured and unruptured aneurysms may yield risk factors for rupture. Data on changes of geometric measures associated with rupture are, however, sparse, because patients with ruptured aneurysms rarely have undergone previous imaging of the intracranial vasculature. We had the opportunity to assess 3D geometric differences of aneurysms before and after rupture. The purpose of this study was to evaluate possible differences between prerupture and postrupture imaging of a ruptured intracranial aneurysm.Materials and methodsUsing high-quality 3D image data, we generated 3D geometric models before and after rupture and compared these for changes in aneurysm volume and displacement. A neuroradiologist qualitatively assessed aneurysm shape change, the presence of perianeurysmal hematoma, and subsequent mass effect exerted on aneurysm and parent vessels.ResultsAneurysm volume was larger in the postrupture imaging in 7 of 9 aneurysms, with a median increase of 38% and an average increase of 137%. Three aneurysms had new lobulations on postrupture imaging; 2 other aneurysms were displaced up to 5 mm and had changed in geometry due to perianeurysmal hematoma.ConclusionsGeometric comparisons of aneurysms before and after rupture show a large volume increase, origination of lobulations, and displacement due to perianeurysmal hematoma. Geometric and hemodynamic comparison of series of unruptured and ruptured aneurysms in the search for rupture-risk-related factors should be interpreted with caution.
| S-EPMC7966588 | biostudies-literature
Project description:Background and purposePatients harboring nongiant cerebral aneurysms may rarely present with an ischemic infarct distal to the aneurysm. The aim of this case series was to report clinical and radiologic characteristics of these patients, their management, and outcome.Materials and methodsWe undertook a single-center retrospective analysis of consecutive patients admitted during an 8-year period with an acute ischemic stroke revealing an unruptured nongiant (<25 mm) sacciform intracranial aneurysm. Clinical, radiologic, therapeutic, and follow-up data were analyzed.ResultsNine patients were included. The mean size of aneurysms was 9.6 ± 6 mm, and 5 were partially or totally thrombosed. Two patients had a fatal SAH within 3 days after stroke-symptom onset, whereas asymptomatic meningeal bleeding was diagnosed or suspected in 2 others. Most of the patients with unthrombosed aneurysms were successfully treated by endovascular coiling in the acute phase. Thrombosed aneurysms were usually treated with antithrombotics, and most recanalized secondarily, requiring endovascular treatment or surgical obliteration. No recurrence of an ischemic event or SAH was observed during the 31 ± 12 months of follow-up (from 4 to 53 months).ConclusionsIn this single-center series, the frequency of early SAH in patients with ischemic stroke distal to an unruptured intracranial aneurysm was high. Acute management should be undertaken with care regarding antithrombotic use, and early endovascular coiling should be considered.
| S-EPMC7965994 | biostudies-literature
Project description: Not available
| S-EPMC10642247 | biostudies-literature
Project description:BackgroundAlterations in TNF-? expression have been associated with cerebral aneurysms, but a direct role in formation, progression, and rupture has not been established.MethodsCerebral aneurysms were induced through hypertension and a single stereotactic injection of elastase into the basal cistern in mice. To test the role of TNF-? in aneurysm formation, aneurysms were induced in TNF-? knockout mice and mice pretreated with the synthesized TNF-? inhibitor 3,6'dithiothalidomide (DTH). To assess the role of TNF-? in aneurysm progression and rupture, DTH was started 6 days after aneurysm induction. TNF-? expression was assessed through real-time PCR and immunofluorescence staining.ResultsTNF-? knockout mice and those pre-treated with DTH had significantly decreased incidence of aneurysm formation and rupture as compared to sham mice. As compared with sham mice, TNF-? protein and mRNA expression was not significantly different in TNF-? knockout mice or those pre-treated with DTH, but was elevated in unruptured and furthermore in ruptured aneurysms. Subarachnoid hemorrhage (SAH) occurred between 7 and 21 days following aneurysm induction. To ensure aneurysm formation preceded rupture, additional mice underwent induction and sacrifice after 7 days. Seventy-five percent had aneurysm formation without evidence of SAH. Initiation of DTH treatment 6 days after aneurysm induction did not alter the incidence of aneurysm formation, but resulted in aneurysmal stabilization and a significant decrease in rupture.ConclusionsThese data suggest a critical role of TNF-? in the formation and rupture of aneurysms in a model of cerebral aneurysm formation. Inhibitors of TNF-? could be beneficial in preventing aneurysmal progression and rupture.
| S-EPMC4022343 | biostudies-literature
Project description:BackgroundEstrogen deficiency is thought to be responsible for the higher frequency of aneurysmal subarachnoid hemorrhage in post- than premenopausal women. Estrogen replacement therapy appears to reduce this risk but is associated with significant side effects. We tested our hypothesis that bazedoxifene, a clinically used selective estrogen receptor (ER) modulator with fewer estrogenic side effects, reduces cerebral aneurysm rupture in a new model of ovariectomized rats.MethodsTen-week-old female Sprague-Dawley rats were subjected to ovariectomy, hemodynamic changes, and hypertension to induce aneurysms (ovariectomized aneurysm rats) and treated with vehicle or with 0.3 or 1.0 mg/kg/day bazedoxifene. They were compared with sham-ovariectomized rats subjected to hypertension and hemodynamic changes (HT rats). The vasoprotective effects of bazedoxifene and the mechanisms underlying its efficacy were analyzed.ResultsDuring 12 weeks of observation, the incidence of aneurysm rupture was 52% in ovariectomized rats. With no effect on the blood pressure, treatment with 0.3 or 1.0 mg/kg/day bazedoxifene lowered this rate to 11 and 17%, almost the same as in HT rats (17%). In ovariectomized rats, the mRNA level of ER?, ER?, and the tissue inhibitor of metalloproteinase-2 was downregulated in the cerebral artery prone to rupture at 5 weeks after aneurysm induction; the mRNA level of interleukin-1? and the matrix metalloproteinase-9 was upregulated. In HT rats, bazedoxifene restored the mRNA level of ER? and ER? and decreased the level of interleukin-1? and matrix metalloproteinase-9. These findings suggest that bazedoxifene was protective against aneurysmal rupture by alleviating the vascular inflammation and degradation exacerbated by the decrease in ER? and ER?.ConclusionsOur observation that bazedoxifene decreased the incidence of aneurysmal rupture in ovariectomized rats warrants further studies to validate this response in humans.
| S-EPMC5625708 | biostudies-literature