Morphological predictors of middle cerebral artery bifurcation aneurysm rupture

Impact of preaneurysmal M1 length in unruptured middle cerebral artery aneurysm: mid-term outcome and single-center experience

OBJECTIVE

This study was design to investigate the surgical and functional outcome based on the preaneurysmal M1 length for unruptured MCA aneurysm.

METHODS

Among 250 consecutive patients with unruptured aneurysms operated in our institution between 2015 and 2017, 72 were MCA aneurysms. Risk factors for IR (i.e., intraoperative rupture) were investigated including age, sex, preaneurysmal M1 length, maximal MCA aneurysm diameter, neck size, aneurysm shape, sphenoid ridge proximation sign. Outcome was measured at discharge, 1 yr and last follow-up. Outcome was compared according to the preaneurysmal M1 length.

RESULTS

Among 68 patients included, five patients (7.3%) suffered IR. Mean maximal diameter of MCA aneurysm (7.9 mm ± 3.4 vs. 4.5 ± 1.8; p = 0.01) was significantly associated with IR risk. Mean M1 length seemed to be shorter in the IR group although not statistically significant (16.2 mm ± 5.1 vs. 11.5 mm ± 4.8; p = 0.053). Mid-term outcome was favorable for all patients at last follow-up but was worsen in case of short preaneurysmal M1 segment (10.7 mm ± 4.8 vs. 16.4 mm ± 5.3, p = 0.02). Complete aneurysm occlusion was achieved for sixty-nine patients (95.5%) with 6.9% of early postoperative complications.

CONCLUSIONS

The microsurgical treatment of unruptured MCA aneurysm was associated with favorable mid-term outcome in all patients and high rates of complete occlusion. Aneurysm size was significantly associated with the intraoperative rupture risk for unruptured MCA aneurysm and patients with a short preaneurysmal M1 segment seemed to have a greater risk of intraoperative rupture although not statistically significant. Short preaneurysmal M1 patients had worsen mid-term outcome.

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.

Combining Machine-Measured Morphometric, Geometric, and Hemodynamic Factors to Predict the Risk of Aneurysm Rupture at the Middle Cerebral Artery Bifurcation

BACKGROUND

Middle Cerebral Artery Bifurcation Aneurysm (MbifA) is associated with a high risk of rupture and poor overall prognosis in patients once it ruptures. Morphological, geometric, and hemodynamic parameters have been identified as factors contributing to the rupture of intracranial aneurysms. However, there are no studies that combine these 3 types of parameters to specifically target MbifA rupture.

METHODS

This study enrolled all patients with MbifAs diagnosed at our treatment center from 1 April 2021 to 31 July 2023 who met the study criteria. All patients underwent digital subtraction angiography examination to obtain 3D rotational angiography data. We imported the complete image data into the Aneurysm/Artery Reconstruction and Analysis machine to obtain 13 morphological parameters (Dneck, Ddome, Height, Dmax, Dartery, aspect ratio [AR], size ratio, dome-neck-ratio [DNR], height-artery-ratio, bottleneck factor, Inflow Angle, Incline Angle, Arterial Angle), 5 geometric parameters (V,S,undulation index [UI], ellipticity index [EI],nonsphericity index [NSI]), and 5 hemodynamic parameters (wall shear stress [WSS], the maximum WSS, the parent artery WSS, the normalized WSS [NWSS], oscillatory shear index [OSI]). All the above significant parameters were tested by univariate and multivariate analyses to find out the independent discriminatory factors.

RESULTS

A total of 49 MbifAs (16 ruptured and 33 unruptured) from 44 patients were included in the study. Height (P = 0.033), AR (P = 0.007), DNR (P = 0.011), EI (P = 0.042), NSI(P = 0.030), UI(P = 0.027), WSS(P = 0.033), and NWSS(P = 0.002) were all associated with MbifA rupture in univariate analyses, but only NWSS was an independent risk factor (P = 0.036, OR = 0.046, 95% CI: 0.003-0.815) in multivariate logistic regression analysis.

CONCLUSIONS

Height, AR, DNR, EI, UI, NSI, WSS, and NWSS may be correlated with MbifA rupture, but only NWSS was an independent risk factor. A lower NWSS was associated with a higher risk of MbifA rupture. No significant differences were observed in the angle parameters, including the Inflow Angle, between ruptured and unruptured MbifAs. OSI was significantly increased at the dome of the aneurysm but the mean OSI was not found to be associated with MbifA rupture.

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.

Predicting the formation of mixed pattern hemorrhages in ruptured middle cerebral artery aneurysms based on a decision tree model: A multicenter study

OBJECTIVE

Mixed-pattern hemorrhages (MPH) commonly occur in ruptured middle cerebral artery (MCA) aneurysms and are associated with poor clinical outcomes. This study aimed to predict the formation of MPH in a multicenter database of MCA aneurysms using a decision tree model.

METHODS

We retrospectively reviewed patients with ruptured MCA aneurysms between January 2009 and June 2020. The MPH was defined as subarachnoid hemorrhages with intracranial hematomas and/or intraventricular hemorrhages and/or subdural hematomas. Univariate and multivariate logistic regression analyses were used to explore the prediction factors of the formation of MPH. Based on these prediction factors, a decision tree model was developed to predict the formation of MPH. Additional independent datasets were used for external validation.

RESULTS

We enrolled 436 patients with ruptured MCA aneurysms detected by computed tomography angiography; 285 patients had MPH (65.4%). A multivariate logistic regression analysis showed that age, aneurysm size, multiple aneurysms, and the presence of a daughter dome were the independent prediction factors of the formation of MPH. The areas under receiver operating characteristic curves of the decision tree model in the training, internal, and external validation cohorts were 0.951, 0.927, and 0.901, respectively.

CONCLUSION

Age, aneurysm size, the presence of a daughter dome, and multiple aneurysms were the independent prediction factors of the formation of MPH. The decision tree model is a useful visual triage tool to predict the formation of MPH that could facilitate the management of unruptured aneurysms in routine clinical work.

Predicting the rupture status of small middle cerebral artery aneurysms using random forest modeling

Objective

Small intracranial aneurysms are increasingly being detected; however, a prediction model for their rupture is rare. Random forest modeling was used to predict the rupture status of small middle cerebral artery (MCA) aneurysms with morphological features.

Methods

From January 2009 to June 2020, we retrospectively reviewed patients with small MCA aneurysms (<7 mm). The aneurysms were randomly split into training (70%) and internal validation (30%) cohorts. Additional independent datasets were used for the external validation of 78 small MCA aneurysms from another four hospitals. Aneurysm morphology was determined using computed tomography angiography (CTA). Prediction models were developed using the random forest and multivariate logistic regression.

Results

A total of 426 consecutive patients with 454 small MCA aneurysms (<7 mm) were included. A multivariate logistic regression analysis showed that size ratio (SR), aspect ratio (AR), and daughter dome were associated with aneurysm rupture, whereas aneurysm angle and multiplicity were inversely associated with aneurysm rupture. The areas under the receiver operating characteristic (ROC) curves (AUCs) of random forest models using the five independent risk factors in the training, internal validation, and external validation cohorts were 0.922, 0.889, and 0.92, respectively. The random forest model outperformed the logistic regression model (p = 0.048). A nomogram was developed to assess the rupture of small MCA aneurysms.

Conclusion

Random forest modeling is a good tool for evaluating the rupture status of small MCA aneurysms and may be considered for the management of small aneurysms.

Irregular Pulsation of Intracranial Aneurysm Detected by Four-Dimensional CT Angiography and Associated With Small Aneurysm Rupture: A Single-Center Prospective Analysis

Objectives

Predicting the risk of rupture of small intracranial aneurysms remains challenging. The irregular pulsation of aneurysms detected by four-dimensional CT angiography (4D-CTA) could be an imaging marker of aneurysm vulnerability. We aimed to investigate the association of irregular pulsation with small aneurysm rupture.

Materials and Methods

This was a prospective study on intracranial aneurysms detected by 4D-CTA from October 2017 to January 2020. A total of 242 consecutive patients with 316 aneurysms were enrolled. Irregular pulsation was defined as a temporary focal protuberance on more than 3 consecutive frames of the 20 phases in the RR interval. Small aneurysms were defined as those <7 mm. Univariate and multivariate analyses were performed to determine the independent predictors of small aneurysm rupture.

Results

A total of 169 patients with 217 small intracranial aneurysms were included. Fourteen (6.5%) of the aneurysms had ruptured, and 77 (35.5%) had irregular pulsation. There were no significant differences in age, sex, hypertension, smoking, diabetes, drinking, or hyperlipidemia between the ruptured and unruptured aneurysm groups. The univariate analysis showed that smaller vessel size (p = 0.008), larger size ratio (p = 0.003), larger aspect ratio (p = 0.006), larger flow angle (p = 0.001), large vessel angle (p = 0.004), middle cerebral artery aneurysms (p = 0.046), anterior cerebral artery/posterior communicating artery/posterior circulation aneurysm (p = 0.006), irregular aneurysm (p = 0.001), and t presence of irregular pulsation (p = 0.001) were associated with small aneurysm rupture. The multivariate analysis showed that the presence of irregular pulsation (p = 0.003), anterior cerebral artery/posterior communicating artery/posterior circulation aneurysms (p = 0.014), and larger flow angle (p = 0.006) was independently associated with aneurysm rupture. Multivariate analysis of predictors of the irregular pulsation of small aneurysms showed that the aneurysm rupture (p = 0.022), irregular aneurysm (p < 0.001), and large size ratio (p = 0.005) were independently associated with the presence of irregular pulsation.

Conclusions

The ruptured small aneurysms more often had irregular pulsation. The irregular pulsation was independently associated with aneurysm rupture and may help evaluate the risk of rupture of small intracranial aneurysms.

Classifying Ruptured Middle Cerebral Artery Aneurysms With a Machine Learning Based, Radiomics-Morphological Model: A Multicentral Study

Objective

Radiomics and morphological features were associated with aneurysms rupture. However, the multicentral study of their predictive power for specific-located aneurysms rupture is rare. We aimed to determine robust radiomics features related to middle cerebral artery (MCA) aneurysms rupture and evaluate the additional value of combining morphological and radiomics features in the classification of ruptured MCA aneurysms.

Methods

A total of 632 patients with 668 MCA aneurysms (423 ruptured aneurysms) from five hospitals were included. Radiomics and morphological features of aneurysms were extracted on computed tomography angiography images. The model was developed using a training dataset (407 patients) and validated with the internal (152 patients) and external validation (73 patients) datasets. The support vector machine method was applied for model construction. Optimal radiomics, morphological, and clinical features were used to develop the radiomics model (R-model), morphological model (M-model), radiomics-morphological model (RM-model), clinical-morphological model (CM-model), and clinical-radiomics-morphological model (CRM-model), respectively. A comprehensive nomogram integrating clinical, morphological, and radiomics predictors was generated.

Results

We found seven radiomics features and four morphological predictors of MCA aneurysms rupture. The R-model obtained an area under the receiver operating curve (AUC) of 0.822 (95% CI, 0.776, 0.867), 0.817 (95% CI, 0.744, 0.890), and 0.691 (95% CI, 0.567, 0.816) in the training, temporal validation, and external validation datasets, respectively. The RM-model showed an AUC of 0.848 (95% CI, 0.810, 0.885), 0.865 (95% CI, 0.807, 0.924), and 0.721 (95% CI, 0.601, 0.841) in the three datasets. The CRM-model obtained an AUC of 0.856 (95% CI, 0.820, 0.892), 0.882 (95% CI, 0.828, 0.936), and 0.738 (95% CI, 0.618, 0.857) in the three datasets. The CRM-model and RM-model outperformed the CM-model and M-model in the internal datasets (p < 0.05), respectively. But these differences were not statistically significant in the external dataset. Decision curve analysis indicated that the CRM-model obtained the highest net benefit for most of the threshold probabilities.

Conclusion

Robust radiomics features were determined related to MCA aneurysm rupture. The RM-model exhibited good ability in classifying ruptured MCA aneurysms. Integrating radiomics features into conventional models might provide additional value in ruptured MCA aneurysms classification.

Aneurysm morphological prediction of intracranial aneurysm rupture in elderly patients using four-dimensional CT angiography

OBJECTIVE

The natural history of unruptured intracranial aneurysms (UIAs) in elderly patients remains poorly understood, and the treatment of UIAs is controversial. The presence of irregular pulsation detected by four-dimensional CT angiography (4D-CTA) is associated with ruptured aneurysms. We aimed to investigate the morphological predictors of irregular pulsation of aneurysms in elderly patients.

PATIENTS AND METHODS

We performed a prospective study of intracranial aneurysms detected by 4D-CTA. Elderly patients were defined as those more than 60 years of age. The irregular pulsation was defined as a focal protuberance during a cardiac cycle. We performed multivariate analyses to determine the associations of clinical characteristics and aneurysm morphologies with the irregular pulsation of aneurysms.

RESULTS

A total of 128 elderly patients with 166 intracranial aneurysms was included. The irregular pulsation occurred in 71 (42.8%) aneurysms. The multivariate analysis showed that a large size ratio (p = 0.006), posterior circulation aneurysms (p = 0.033), the presence of a daughter dome (p = 0.006), and aneurysm rupture (p = 0.032) were independently associated with the irregular pulsation. The multivariate analysis of predictors of irregular pulsation of unruptured aneurysms showed that size ratio (p = 0.01) and the presence of a daughter dome (p = 0.016) were independent predictors of irregular pulsation.

CONCLUSION

A large size ratio, posterior circulation aneurysms, the presence of a daughter dome, and aneurysm rupture were independent predictors of the irregular pulsation of aneurysms in elderly patients. The morphological characteristics detected by 4D-CTA may be helpful to evaluate the risk of rupture of aneurysms.