Hemodynamic and morphological differences in cerebral aneurysms between before and after rupture

Predicting Intracranial Aneurysm Rupture: A Multifactor Analysis Combining Radscore, Morphology, and PHASES Parameters

RATIONALE AND OBJECTIVES

We aimed at developing and validating a nomogram and machine learning (ML) models based on radiomics score (Radscore), morphology, and PHASES to predict intracranial aneurysm (IA) rupture.

MATERIALS AND METHODS

We collected 440 patients with IAs in our hospital from 2015 to 2023, totaling 475 IAs (214 ruptured and 261 unruptured). A 7:3 random split was utilized to allocate participants into training and testing sets. To optimize the selection of radiomics features extracted from digital subtraction angiography, we employed t-tests and LASSO regression. Subsequently, we built single-factor and multifactor logistic regression (LR) models, alongside a nomogram. Furthermore, we employed four ML algorithms. After a comprehensive evaluation, including area under the curve (AUC), calibration curves, decision curve analysis (DCA), and other metrics, the best model was determined.

RESULTS

The AUCs for LR models P (PHASES), M (Morphology), and R (Radscore) in the testing set were 0.859, 0.755, and 0.803, respectively, while those for multifactor models R+M (Radscore and Morphology), R+P (Radscore and PHASES), and R+M+P (Radscore, Morphology, and PHASES) were 0.818, 0.899, and 0.887, respectively. The AUCs of random forest, extreme gradient boosting, gradient boosting machine, and light gradient boosting machine were 0.880, 0.888, 0.891, and 0.892 in testing set, respectively. In the training set, the LR model showed significant differences in AUCs compared with the four ML models (all p < 0.05). However, in the testing set, no statistically significant differences were found between them (all p > 0.05). Both ML models and the nomogram exhibit excellent performance in DCA and calibration curves.

CONCLUSION

Nomogram and ML models based on Radscore, morphology, and PHASES show high precision in predicting aneurysm rupture.

Integrating PointNet-Based Model and Machine Learning Algorithms for Classification of Rupture Status of IAs

BACKGROUND

The rupture of intracranial aneurysms (IAs) would result in subarachnoid hemorrhage with high mortality and disability. Predicting the risk of IAs rupture remains a challenge.

METHODS

This paper proposed an effective method for classifying IAs rupture status by integrating a PointNet-based model and machine learning algorithms. First, medical image segmentation and reconstruction algorithms were applied to 3D Digital Subtraction Angiography (DSA) imaging data to construct three-dimensional IAs geometric models. Geometrical parameters of IAs were then acquired using Geomagic, followed by the computation of hemodynamic clouds and hemodynamic parameters using Computational Fluid Dynamics (CFD). A PointNet-based model was developed to extract different dimensional hemodynamic cloud features. Finally, five types of machine learning algorithms were applied on geometrical parameters, hemodynamic parameters, and hemodynamic cloud features to classify and recognize IAs rupture status. The classification performance of different dimensional hemodynamic cloud features was also compared.

RESULTS

The 16-, 32-, 64-, and 1024-dimensional hemodynamic cloud features were extracted with the PointNet-based model, respectively, and the four types of cloud features in combination with the geometrical parameters and hemodynamic parameters were respectively applied to classify the rupture status of IAs. The best classification outcomes were achieved in the case of 16-dimensional hemodynamic cloud features, the accuracy of XGBoost, CatBoost, SVM, LightGBM, and LR algorithms was 0.887, 0.857, 0.854, 0.857, and 0.908, respectively, and the AUCs were 0.917, 0.934, 0.946, 0.920, and 0.944. In contrast, when only utilizing geometrical parameters and hemodynamic parameters, the accuracies were 0.836, 0.816, 0.826, 0.832, and 0.885, respectively, with AUC values of 0.908, 0.922, 0.930, 0.884, and 0.921.

CONCLUSION

In this paper, classification models for IAs rupture status were constructed by integrating a PointNet-based model and machine learning algorithms. Experiments demonstrated that hemodynamic cloud features had a certain contribution weight to the classification of IAs rupture status. When 16-dimensional hemodynamic cloud features were added to the morphological and hemodynamic features, the models achieved the highest classification accuracies and AUCs. Our models and algorithms would provide valuable insights for the clinical diagnosis and treatment of IAs.

Monitoring of Perioperative Microcirculation Dysfunction by Near-Infrared Spectroscopy for Neurological Deterioration and Prognosis of Aneurysmal Subarachnoid Hemorrhage: An Observational, Longitudinal Cohort Study

INTRODUCTION

No evidence has established a direct causal relationship between early microcirculation disturbance after aneurysmal subarachnoid hemorrhage (aSAH) and neurological function prognosis, which is the key pathophysiological mechanism of early brain injury (EBI) in patients with aSAH.

METHODS

A total of 252 patients with aSAH were enrolled in the Neurosurgical Intensive Care Unit of Southwest Hospital between January 2020 and December 2022 and divided into the no neurological deterioration, early neurological deterioration, and delayed neurological deterioration groups. Indicators of microcirculation disorders in EBI included regional cerebral oxygen saturation (rSO2) measured by near-infrared spectroscopy (NIRS), brain oxygen monitoring, and other clinical parameters for evaluating neurological function and determining the prognosis of patients with aSAH.

RESULTS

Our data suggest that the rSO2 is generally lower in patients who develop neurological deterioration than in those who do not and that there is at least one time point in the population of patients who develop neurological deterioration where left and right cerebral hemisphere differences can be significantly monitored by NIRS. An unordered multiple-classification logistic regression model was constructed, and the results revealed that multiple factors were effective predictors of early neurological deterioration: reoperation, history of brain surgery, World Federation of Neurosurgical Societies (WFNS) grade 4-5, Fisher grade 3-4, SAFIRE grade 3-5, abnormal serum sodium and potassium levels, and reduced rSO2 during the perioperative period. However, for delayed neurological deterioration in patients with aSAH, only a history of brain surgery and perioperative RBC count were predictive indicators.

CONCLUSIONS

The rSO2 concentration in patients with neurological deterioration is generally lower than that in patients without neurological deterioration, and at least one time point in the population with neurological deterioration can be significantly monitored via NIRS. However, further studies are needed to determine the role of microcirculation and other predictive factors in the neurocritical management of EBI after aSAH, as these factors can reduce the incidence of adverse outcomes and mortality during hospitalization.

Three-Dimensional Morphological Change of Intracranial Aneurysms Before and Around Rupture

BACKGROUND AND OBJECTIVES

Patients with an unruptured intracranial aneurysm often undergo periodic imaging to detect potential aneurysm growth, which is associated with an increased rupture risk. Because prediction of rupture based on growth is moderate, morphological changes have gained interest as a risk factor for rupture. We studied 3-dimensional-quantified morphological changes over time during radiological monitoring before rupture and around rupture.

METHODS

In this retrospective observational study, we identified aneurysms that ruptured during follow-up, with imaging available for at least 2 time points before rupture and one after rupture. For each time point, we obtained 8 morphological parameters: 2-dimensional size, volume, surface area, compactness 1 and 2, sphericity, elongation, and flatness. Morphological changes before rupture and around rupture were log-transformed, scaled, and analyzed with linear mixed-effects models.

RESULTS

We included 16 aneurysms in 16 patients who were imaged between 2004 and 2021. In the time period before rupture (median follow-up duration 1200 days, IQR 736-1340), 3 size-related morphological parameters increased: 2-dimensional size (estimated mean change 0.44, 95% CI 0.24-0.65), volume (estimated mean change 0.34, 95% CI 0.12-0.56), and surface area (0.33, 95% CI 0.11-0.54). In the period around rupture (median follow-up duration 407 days, IQR 148-719), these parameters further increased. In addition, 5 morphological parameters (compactness 1 and 2, sphericity, elongation, and flatness) decreased around rupture but not before rupture.

CONCLUSION

Change in aneurysm volume and surface area may be novel risk factors for rupture. Because most morphological parameters changed around but not before rupture, morphological changes during these 2 periods should be regarded as different processes. This implies that postrupture morphology should not be used as a surrogate for prerupture morphology in rupture prediction models.