Prediction of internal carotid artery aneurysm recurrence by pressure difference at the coil mass surface

Impact Exploration of Spatiotemporal Feature Derivation and Selection on Machine Learning-Based Predictive Models for Post-Embolization Cerebral Aneurysm Recanalization

PURPOSE

To enhance the performance of machine learning (ML) models for the post-embolization recanalization of cerebral aneurysms, we evaluated the impact of hemodynamic feature derivation and selection method on six ML algorithms.

METHODS

We utilized computational fluid dynamics (CFD) to simulate hemodynamics in 66 cerebral aneurysms from 65 patients, including 57 stable and nine recanalized aneurysms. We derived a total of 107 features for each aneurysm, encompassing four clinical features, 12 morphological features, and 91 hemodynamic features. To investigate the influence of feature derivation and selection methods on the ML models, we employed two derivation methods, simplified and fully derived, in combination with four selection methods: all features, statistically significant analysis, stepwise multivariate logistic regression analysis (stepwise-LR), and recursive feature elimination (RFE). Model performance was assessed using the area under the receiver operating characteristic curve (AUROC) and precision-recall curve (AUPRC) on both the training and testing datasets.

RESULTS

The AUROC values on the testing dataset exhibited a wide-ranging spectrum, spanning from 0.373 to 0.863. Fully derived features and the RFE selection method demonstrated superior performance in intra-model comparisons. The multi-layer perceptron (MLP) model, trained with RFE-selected fully derived features, achieved the best performance on the testing dataset, with an AUROC value of 0.863 (95% CI: 0.684- 1.000).

CONCLUSION

Our study demonstrated the importance of feature derivation and selection in determining the performance of ML models. This enabled the development of accurate decision-making models without the need to invade the patient.

Determination of Significant Three-Dimensional Hemodynamic Features for Postembolization Recanalization in Cerebral Aneurysms Through Explainable Artificial Intelligence

BACKGROUND

Recanalization poses challenges after coil embolization in cerebral aneurysms. Establishing predictive models for postembolization recanalization is important for clinical decision making. However, conventional statistical and machine learning (ML) models may overlook critical parameters during the initial selection process.

METHODS

In this study, we automated the identification of significant hemodynamic parameters using a PointNet-based deep neural network (DNN), leveraging their three-dimensional spatial features. Further feature analysis was conducted using saliency mapping, an explainable artificial intelligence (XAI) technique. The study encompassed the analysis of velocity, pressure, and wall shear stress in both precoiling and postcoiling models derived from computational fluid dynamics simulations for 58 aneurysms.

RESULTS

Velocity was identified as the most pivotal parameter, supported by the lowest P value from statistical analysis and the highest area under the receiver operating characteristic curves/precision-recall curves values from the DNN model. Moreover, visual XAI analysis showed that robust injection flow zones, with notable impingement points in precoiling models, as well as pronounced interplay between flow dynamics and the coiling plane, were important three-dimensional features in identifying the recanalized aneurysms.

CONCLUSIONS

The combination of DNN and XAI was found to be an accurate and explainable approach not only at predicting postembolization recanalization but also at discovering unknown features in the future.

Fluid dynamic analysis in predicting the recanalization of intracranial aneurysms after coil embolization - A study of spatiotemporal characteristics

Purpose

Hemodynamics play a key role in the management of cerebral aneurysm recanalization after coil embolization; however, the most reliable hemodynamic parameter remains unknown. Previous studies have explored the use of both spatiotemporally averaged and maximal definitions for hemodynamic parameters, based on computational fluid dynamics (CFD) analysis, to build predictive models for aneurysmal recanalization. In this study, we aimed to assess the influence of different spatiotemporal characteristics of hemodynamic parameters on predictive performance.

Methods

Hemodynamics were simulated using CFD for 66 cerebral aneurysms from 65 patients. We evaluated 14 types of spatiotemporal definitions for two hemodynamic parameters in the pre-coiling model and five in virtual post-coiling model (VM) created by cutting the aneurysm from the pre-coiling model. A total of 91 spatiotemporal hemodynamic features were derived and utilized to develop univariate predictor (UP) and multivariate logistic regression (LR) models. The model's performance was assessed using two metrics: the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC).

Results

Different spatiotemporal hemodynamic features exhibited a wide range of AUROC values ranging from 0.224 to 0.747, with 22 feature pairs showing a significant difference in AUROC value (P-value <0.05), despite being derived from the same hemodynamic parameter. PDave,q1 was identified as the strongest UP with AUROC/AUPRC values of 0.747/0.385, yielding sensitivity and specificity value of 0.889 and 0.614 at the optimal cut-off value, respectively. The LR model further improved the prediction performance, having AUROC/AUPRC values of 0.890/0.903. At the optimal cut-off value, the LR model achieved a specificity of 0.877, sensitivity of 0.719, outperforming the UP model.

Conclusion

Our research indicated that the characteristics of hemodynamic parameters in terms of space and time had a significant impact on the development of predictive model. Our findings suggest that LR model based on spatiotemporal hemodynamic features could be clinically useful in predicting recanalization after coil embolization in patients, without the need for invasive procedures.

Progression from Early Minor Recanalization to Major Recanalization in Ruptured Intracranial Aneurysms After Successful Coil Embolization: Risk Factors and Proposal of a Novel Predicting Variable

BACKGROUND

The risk factors for the progression from early minor recanalization to major recanalization are not well established. Herein, we evaluated ruptured intracranial aneurysms (IAs) with minor recanalization within 1 year of coiling and their progression to major recurrence.

METHODS

We retrospectively reviewed our database of coiled IAs and searched for ruptured saccular IAs that were successfully embolized without residual sacs. We selected IAs with minor recanalization confirmed on radiological studies within 1 year of coil embolization. All the IA cases had a follow-up period longer than 36 months based on the radiological results.

RESULTS

Minor recanalization occurred in 45 IAs within 1 year of coil embolization. Among them, 14 IAs (31.1%) progressed to major recanalization, and 31 remained stable. Progression to major recanalization was detected 12 months after minor recanalization in 2 patients, 24 months in 7 patients, and 36 months in 5 patients. Moreover, the progression to major recanalization occurred more frequently in IAs at the posterior location (P = 0.024, odds ratio 11.20) and IAs with a proportional forced area > 9 mm2 (P = 0.002, odds ratio 17.13), which was a newly proposed variable in the present study.

CONCLUSIONS

Our results showed that approximately one third of the ruptured IAs with early minor recanalization after coiling progressed to major recanalization within 3 years. Physicians should focus on the progression of ruptured IAs from minor to major recanalization, especially those with a posterior circulation location and a proportional forced area >9 mm2.

Hemodynamic factor evaluation using computational fluid dynamics analysis for de novo bleb formation in unruptured intracranial aneurysms

Background

Although bleb formation increases the risk of rupture of intracranial aneurysms, previous computational fluid dynamic (CFD) studies have been unable to identify robust causative hemodynamic factors, due to the morphological differences of prebleb aneurysm models and a small number of aneurysms with de novo bleb formation. This study investigated the influences of differences in the aneurysm-models and identify causative hemodynamic factors for de novo bleb formation.

Materials and methods

CFD analysis was conducted on three aneurysm models, actual prebleb, postbleb, and virtual prebleb models of two unruptured aneurysms with de novo bleb formation. A new multipoint method was introduced in this study. We evenly distributed points with a 0.5-mm distance on the aneurysm surface of the actual prebleb models (146 and 152 points in the individual aneurysm, respectively), and we statistically compared hemodynamics at the points in the areas with and without bleb formation (19 and 279 points, respectively).

Results

Visually, blebs formed on an aneurysm surface area with similar hemodynamic characteristics in the actual and virtual prebleb models. Statistical analysis using the multipoint method revealed that the de novo bleb formation area was significantly correlated with high pressure (p < 0.001), low wall shear stress (WSS) (p < 0.001), and the center of divergent WSS vectors (p = 0.025).

Conclusions

De novo bleb formation in intracranial aneurysms may occur in areas associated with the combination of high pressure, low WSS, and the center of divergent WSS vectors. The multipoint method is useful for statistical analysis of hemodynamics in a limited number of aneurysms.