RESUMEN
BACKGROUND: Maximum wall shear stress (maxWSS) points of unruptured cerebral aneurysms (UCAs) may cause wall remodeling leading to rupture. We characterized maxWSS points and their inherent intra-aneurysmal flow structures in a sizable cohort of saccular UCAs using four-dimensional (4D) flow magnetic resonance imaging (MRI). METHODS: After contrast administration, 50 saccular UCAs were subjected to 4D flow MRI using a 1.5â¯T MRI scanner. Post-processing of obtained data was performed using commercially available software. The maxWSS points and maxWSS values were evaluated. The maxWSS values were statistically compared between aneurysm groups. RESULTS: The maxWSS point was located on the aneurysm apex in 9 (18.0%), body in 2 (4.0%), and neck in 39 (78.0%) UCAs. The inherent intra-aneurysmal flow structure of the maxWSS point was an inflow zone in 34 (68.0%) UCAs, an inflow jet in 8 (16.0%), and an impingement zone in 8 (16.0%). The maxWSS point on the neck had significantly higher maxWSS values than those points on the other wall areas (Pâ¯= 0.008). The maxWSS values of the maxWSS points on the apex and on the impingement zone were not significantly different compared with those of the other maxWSS points. CONCLUSION: The maxWSS points existed preferentially on the aneurysmal neck adjacent to the inflow zone with higher maxWSS values. The maxWSS points existed occasionally on the aneurysmal apex adjacent to the impingement zone. 4D flow MRI may be helpful to discriminate saccular UCAs with higher-risk maxWSS points that can cause wall remodeling leading to rupture.
RESUMEN
[This corrects the article DOI: 10.1371/journal.pone.0261996.].
RESUMEN
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.
Asunto(s)
Embolización Terapéutica , Hemodinámica , Aneurisma Intracraneal , Aprendizaje Automático , Modelos Cardiovasculares , Valor Predictivo de las Pruebas , Humanos , Aneurisma Intracraneal/fisiopatología , Aneurisma Intracraneal/terapia , Aneurisma Intracraneal/diagnóstico por imagen , Persona de Mediana Edad , Masculino , Femenino , Anciano , Resultado del Tratamiento , Circulación Cerebrovascular , Factores de Tiempo , Modelación Específica para el Paciente , Toma de Decisiones Clínicas , Técnicas de Apoyo para la Decisión , AdultoRESUMEN
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.
Asunto(s)
Embolización Terapéutica , Aneurisma Intracraneal , Humanos , Inteligencia Artificial , Aneurisma Intracraneal/diagnóstico por imagen , Aneurisma Intracraneal/terapia , Embolización Terapéutica/métodos , Hemodinámica , Prótesis VascularRESUMEN
BACKGROUND: Extracranial internal carotid artery aneurysms (EICAs) are rare. Although a high mortality risk has been reported in nonoperated cases, the optimal treatment for EICAs remains unknown. OBSERVATIONS: A 79-year-old female presented with painless swelling in the right neck. Imaging revealed a giant EICA with a maximum diameter of 3.2 cm. Superficial temporal artery-middle cerebral artery bypass and internal carotid artery (ICA) trapping were performed. Because the distal aneurysm edge was at the C1 level, the distal portion of the aneurysm was occluded by endovascular coiling, and the proximal portion was surgically ligated. Blood flow into the aneurysm disappeared after the operation. Three years postsurgery, enlargement of the aneurysm with blood flow from the ascending pharyngeal artery (APA) was detected. The EICA was resected after coiling the APA and ligating both ends of the aneurysm. Pathologically, neovascularization within the aneurysm wall was observed. LESSONS: Even if blood flow into an EICA disappears after ICA trapping, the EICAs can enlarge due to neovascularization from the neighboring artery. From the outset, removal of the aneurysm should be considered as a radical treatment strategy for giant EICAs.
RESUMEN
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.