Morphologic Feature Elongation Can Predict Occlusion Status Following Pipeline Embolization of Intracranial Aneurysms

Prediction of small intracranial aneurysm rupture status based on combined Clinical-Radiomics model

Background

Accumulating small unruptured intracranial aneurysms are detected due to the improved quality and higher frequency of cranial imaging, but treatment remains controversial. While surgery or endovascular treatment is effective for small aneurysms with a high risk of rupture, such interventions are unnecessary for aneurysms with a low risk of rupture. Consequently, it is imperative to accurately identify small aneurysms with a low risk of rupture. The purpose of this study was to develop a clinically practical model to predict small aneurysm ruptures based on a radiomics signature and clinical risk factors.

Methods

A total of 293 patients having an aneurysm with a diameter of less than 5 mm, including 199 patients (67.9 %) with a ruptured aneurysm and 94 patients (32.1 %) without a ruptured aneurysm, were included in this study. Digital subtraction angiography or surgical treatment was required in all cases. Data on the clinical risk factors and the features on computed tomography angiography images associated with the aneurysm rupture status were collected simultaneously. We developed a clinical-radiomics model to predict aneurysm rupture status using multivariate logistic regression analysis. The combined clinical-radiomics model was constructed by nomogram analysis. The diagnostic performance, clinical utility, and model calibration were evaluated by operating characteristic curve analysis, decision curve analysis, and calibration analysis.

Results

A combined clinical-radiomics model (Area Under Curve [AUC], 0.85; 95 % confidence interval [CI], 0.757-0.947) showed effective performance in the operating characteristic curve analysis. In the validation cohort, the performance of the combined model was better than that of the radiomics model (AUC, 0.75; 95 % CI, 0.645-0.865; Delong's test p-value = 0.01) and the clinical model (AUC, 0.74; 95 % CI, 0.625-0.851; Delong's test p-value <0.01) alone. The results of the decision curve, nomogram, and calibration analyses demonstrated the clinical utility and good fitness of the combined model.

Conclusion

Our study demonstrated the effectiveness of a clinical-radiomics model for predicting rupture status in small aneurysms.

MR Imaging of the Cerebral Aneurysmal Wall for Assessment of Rupture Risk

The evaluation of unruptured intracranial aneurysms requires a comprehensive and multifaceted approach. The comprehensive analysis of aneurysm wall enhancement through high-resolution MRI, in tandem with advanced processing techniques like finite element analysis, quantitative susceptibility mapping, and computational fluid dynamics, has begun to unveil insights into the intricate biology of aneurysms. This enhanced understanding of the etiology, progression, and eventual rupture of aneurysms holds the potential to be used as a tool to triage patients to intervention versus observation. Emerging tools such as radiomics and machine learning are poised to contribute significantly to this evolving landscape of diagnostic refinement.

Inflow Angle and Height-Width Ratio are Predictors of Incomplete Occlusion at One and Two Years After Flow Diverter Treatment for Small- and Medium-Sized Internal Carotid Artery Aneurysms

OBJECTIVE

We investigated the association between the inflow angle of aneurysms and their occlusion status at 1 and 2 years after flow diverter (FD) treatment.

METHODS

We retrospectively analyzed 42 consecutive patients from a single center with 43 untreated, unruptured internal carotid artery (ICA) proximal to communicating segment, saccular aneurysms sized <12 mm.

RESULTS

At 1 year posttreatment, the complete occlusion (CO) rate was 58.1%. On univariate analyses, the proportion of inflow angle >90° was significantly lower in the CO group than in the incomplete occlusion group (20.0% VS. 83.3%; P < 0.001). The CO incidence decreased with a height-width (H/W) ratio of <1.2 (P = 0.059). On multivariate analysis, an H/W ratio of <1.2 (odds ratio [OR], 0.076; P = 0.027) and an inflow angle of >90° (OR, 0.020; P = 0.0011) significantly influenced CO at 1 year post FD. At 2 years posttreatment, the CO rate was 76.3% (29/38 cases with available follow-up data). On univariate analyses, in the CO group compared to the incomplete occlusion group, the proportion of H/W ratio <1.2 was significantly lower (P = 0.005) and the proportion of inflow angle >90° was significantly lower (P = 0.021); aneurysm dome size tended to be larger (8.5 mm vs. 7.1 mm; P = 0.080). On multivariate analysis, an H/W ratio <1.2 (OR, 0.042; P = 0.015) and an inflow angle >90° (OR: 0.088; P = 0.031) significantly influenced CO at 2 years post FD.

CONCLUSIONS

The inflow angle of >90° and H/W ratio <1.2 may significantly influence the CO rate in small- or medium-sized internal carotid artery aneurysms 1 and 2 years post FD.

Augmenting Prediction of Intracranial Aneurysms' Risk Status Using Velocity-Informatics: Initial Experience

Our primary goal here is to demonstrate that innovative analytics of aneurismal velocities, named velocity-informatics, enhances intracranial aneurysm (IA) rupture status prediction. 3D computer models were generated using imaging data from 112 subjects harboring anterior IAs (4-25 mm; 44 ruptured and 68 unruptured). Computational fluid dynamics simulations and geometrical analyses were performed. Then, computed 3D velocity vector fields within the IA dome were processed for velocity-informatics. Four machine learning methods (support vector machine, random forest, generalized linear model, and GLM with Lasso or elastic net regularization) were employed to assess the merits of the proposed velocity-informatics. All 4 ML methods consistently showed that, with velocity-informatics metrics, the area under the curve and prediction accuracy both improved by approximately 0.03. Overall, with velocity-informatics, the support vector machine's prediction was most promising: an AUC of 0.86 and total accuracy of 77%, with 60% and 88% of ruptured and unruptured IAs being correctly identified, respectively.

Morphological features predicting in-stent stenosis after pipeline implantation for unruptured intracranial aneurysm

Purpose

Elongation denotes the regularity of an aneurysm and parent artery. This retrospective research study was conducted to identify the morphological factors that could predict postoperative in-stent stenosis (ISS) after Pipeline Embolization Device (PED) implantation for unruptured intracranial aneurysms (UIAs).

Methods

Patients with UIA and treated with PED at our institute between 2015 and 2020 were selected. Preoperative morphological features including both manually measured shape features and radiomics shape features were extracted and compared between patients with and without ISS. Logistic regression analysis was performed for factors associated with postoperative ISS.

Results

A total of 52 patients (18 men and 34 women) were involved in this study. The mean angiographic follow-up time was 11.87 ± 8.26 months. Of the patients, 20 of them (38.46%) were identified with ISS. Multivariate logistic analysis showed that elongation (odds ratio = 0.008; 95% confidence interval, 0.001-0.255; p = 0.006) was an independent risk factor for ISS. The area under the curve (AUC) of the receiver operating characteristic curve(ROC) was 0.734 and the optimal cut-off value of elongation for ISS classification was 0.595. The sensitivity and specificity of prediction were 0.6 and 0.781, respectively. The ISS degree of elongation of less than 0.595 was larger than the ISS degree of elongation of more than 0.595.

Conclusion

Elongation is a potential risk factor associated with ISS after PED implantation for UIAs. The more regular an aneurysm and parent artery, the less likelihood of an ISS occurrence.

Enhanced Radiomics for Prediction of Rupture Status in Cerebral Aneurysms

BACKGROUND

Radiomics is a powerful tool for automatic extraction of morphological features, but when applied to cerebral aneurysms, it is inferior to established descriptors in classifying rupture status. We sought a strategy to recover neck orientation and parent vessel caliber to enhance Radiomics performance and facilitate its adoption for aneurysm risk stratification.

METHODS

We analyzed 135 sidewall (32 ruptured) and 216 bifurcation (90 ruptured) aneurysms from three-dimensional rotational catheter angiography datasets. Clinical three-dimensional rotational catheter angiography defined in arbitrary orientation underwent affine transformations enabling aneurysm neck alignment to XY plane before analysis in PyRadiomics, facilitating automatic extraction of aneurysm height and width, previously not possible with random alignment. Additionally, parent vessel size was estimated from aneurysm location and incorporated into enhanced Radiomics (height, width, height/width, size ratio). Rupture status classification was compared across methodologies for 31 automatically computed conventional Radiomics, enhanced Radiomics, and established size/shape descriptors using univariate, multivariate, and area under the curve (AUC) statistics.

RESULTS

Enhanced Radiomics-derived height/width and size ratio were significantly higher in both ruptured subsets. Using multivariate analysis in sidewall lesions, enhanced Radiomics (AUC = 0.85) matched established features (AUC = 0.86) and outperformed conventional Radiomics (AUC = 0.82); in bifurcation lesions, enhanced Radiomics (AUC = 0.78) outperformed both established features (AUC = 0.76) and conventional Radiomics (AUC = 0.74).

CONCLUSIONS

Enhanced Radiomics incorporating neck orientation and parent vessel estimate is an efficient operator-independent methodology that offers superior rupture status classification for both sidewall and bifurcation aneurysms and should be considered a strong candidate for larger-scale multicenter and multimodality validation.

Determinants of intracranial aneurysm retreatment following embolization with a single flow-diverting stent

PURPOSE

Flow diverting stents have revolutionized the treatment of intracranial aneurysms through endoluminal reconstruction of the parent vessel. Despite this, certain aneurysms require retreatment. The purpose of this study was to identify clinical and radiologic determinants of aneurysm retreatment following flow diversion.

METHODS

A multicenter flow diversion database was evaluated to identify patients presenting with an unruptured, previously untreated aneurysm with a minimum of 12 months' clinical and angiographic follow-up. Univariate and multivariate logistic regression modeling was performed to identify determinants of retreatment.

RESULTS

We identified 189 aneurysms treated in 189 patients with a single flow-diverting stent. Mean age was 54 years, and 89% were female. Complete occlusion was achieved in 70.3% and 83.6% of patients at six and 12 months, respectively. Aneurysm retreatment with additional flow-diverting stents occurred in 5.8% of cases. Univariate analysis revealed that dome diameter ≥10 mm (p = 0.012), pre-clinoid internal carotid artery location (p = 0.012), distal > proximal parent vessel diameter (p = 0.042), and later dual antiplatelet therapy (DAPT) discontinuation (p < 0.001) were predictive of retreatment. Multivariate analysis identified discontinuation of DAPT >12 months (p = 0.003) as a strong determinant of retreatment with dome diameter ≥10 mm trending toward statistical significance (p = 0.064). Large aneurysm neck diameter, presence of aneurysm branch vessels, patient age, smoking history, and hypertension were not determinant of retreatment on multivariate analysis.

CONCLUSIONS

Prolonged DAPT is the most important determinant of aneurysm retreatment following single-device flow diversion. Abbreviating DAPT duration to only six months should be a consideration in this population, especially for patients with a large aneurysm dome diameter.

Prediction of bleb formation in intracranial aneurysms using machine learning models based on aneurysm hemodynamics, geometry, location, and patient population

BACKGROUND

Bleb presence in intracranial aneurysms (IAs) is a known indication of instability and vulnerability.

OBJECTIVE

To develop and evaluate predictive models of bleb development in IAs based on hemodynamics, geometry, anatomical location, and patient population.

METHODS

Cross-sectional data (one time point) of 2395 IAs were used for training bleb formation models using machine learning (random forest, support vector machine, logistic regression, k-nearest neighbor, and bagging). Aneurysm hemodynamics and geometry were characterized using image-based computational fluid dynamics. A separate dataset with 266 aneurysms was used for model evaluation. Model performance was quantified by the area under the receiving operating characteristic curve (AUC), true positive rate (TPR), false positive rate (FPR), precision, and balanced accuracy.

RESULTS

The final model retained 18 variables, including hemodynamic, geometrical, location, multiplicity, and morphology parameters, and patient population. Generally, strong and concentrated inflow jets, high speed, complex and unstable flow patterns, and concentrated, oscillatory, and heterogeneous wall shear stress patterns together with larger, more elongated, and more distorted shapes were associated with bleb formation. The best performance on the validation set was achieved by the random forest model (AUC=0.82, TPR=91%, FPR=36%, misclassification error=27%).

CONCLUSIONS

Based on the premise that aneurysm characteristics prior to bleb formation resemble those derived from vascular reconstructions with their blebs virtually removed, machine learning models can identify aneurysms prone to bleb development with good accuracy. Pending further validation with longitudinal data, these models may prove valuable for assessing the propensity of IAs to progress to vulnerable states and potentially rupturing.

Morphology-based radiomics signature: a novel determinant to identify multiple intracranial aneurysms rupture

We aimed to develop and validate a morphology-based radiomics signature nomogram for assessing the risk of intracranial aneurysm (IA) rupture. A total of 254 aneurysms in 105 patients with subarachnoid hemorrhage and multiple intracranial aneurysms from three centers were retrospectively reviewed and randomly divided into the derivation and validation cohorts. Radiomics morphological features were automatically extracted from digital subtraction angiography and selected by the least absolute shrinkage and selection operator algorithm to develop a radiomics signature. A radiomics signature-based nomogram was developed by incorporating the signature and traditional morphological features. The performance of calibration, discrimination, and clinical usefulness of the nomogram was assessed. Ten radiomics morphological features were selected to build the radiomics signature model, which showed better discrimination with an area under the curve (AUC) equal to 0.814 and 0.835 in the derivation and validation cohorts compared with 0.747 and 0.666 in the traditional model, which only include traditional morphological features. When radiomics signature and traditional morphological features were combined, the AUC increased to 0.842 and 0.849 in the derivation and validation cohorts, thus showing better performance in assessing aneurysm rupture risk. This novel model could be useful for decision-making and risk stratification for patients with IAs.

A pilot study of radiomics signature based on biparametric MRI for preoperative prediction of extrathyroidal extension in papillary thyroid carcinoma

OBJECTIVE

To investigate efficiency of radiomics signature to preoperatively predict histological features of aggressive extrathyroidal extension (ETE) in papillary thyroid carcinoma (PTC) with biparametric magnetic resonance imaging findings.

MATERIALS AND METHODS

Sixty PTC patients with preoperative MR including T2WI and T2WI-fat-suppression (T2WI-FS) were retrospectively analyzed. Among them, 35 had ETE and 25 did not. Pre-contrast T2WI and T2WI-FS images depicting the largest section of tumor were selected. Tumor regions were manually segmented using ITK-SNAP software and 107 radiomics features were computed from the segmented regions using the open Pyradiomics package. Then, a random forest model was built to do classification in which the datasets were partitioned randomly 10 times to do training and testing with ratio of 1:1. Furthermore, forward greedy feature selection based on feature importance was adopted to reduce model overfitting. Classification accuracy was estimated on the test set using area under ROC curve (AUC).

RESULTS

The model using T2WI-FS image features yields much higher performance than the model using T2WI features (AUC = 0.906 vs. 0.760 using 107 features). Among the top 10 important features of T2WI and T2WI-FS, there are 5 common features. After feature selection, the models trained using top 2 features of T2WI and the top 6 features of T2WI-FS achieve AUC 0.845 and 0.928, respectively. Combining features computed from T2WI and T2WI-FS, model performance decreases slightly (AUC = 0.882 based on all features and AUC = 0.913 based on top features after feature selection). Adjusting hyper parameters of the random forest model have negligible influence on the model performance with mean AUC = 0.907 for T2WI-FS images.

CONCLUSIONS

Radiomics features based on pre-contrast T2WI and T2WI-FS is helpful to predict aggressive ETE in PTC. Particularly, the model trained using the optimally selected T2WI-FS image features yields the best classification performance. The most important features relate to lesion size and the texture heterogeneity of the tumor region.

Performance of Radiomics derived morphological features for prediction of aneurysm rupture status

BACKGROUND

Morphological differences between ruptured and unruptured cerebral aneurysms represent a focus of neuroimaging researchfor understanding the mechanisms of aneurysmal rupture. We evaluated the performance of Radiomics derived morphological features, recently proposed for rupture status classification, against automatically measured shape and size features previously established in the literature.

METHODS

353 aneurysms (123 ruptured) from three-dimensional rotational catheter angiography (3DRA) datasets were analyzed. Based on a literature review, 13 Radiomics and 13 established morphological descriptors were automatically extracted per aneurysm, and evaluated for rupture status prediction using univariate and multivariate statistical analysis, yielding an area under the curve (AUC) metric of the receiver operating characteristic.

RESULTS

Validation of overlapping descriptors for size/volume using both methods were highly correlated (p<0.0001, R ²=0.99). Univariate analysis selected AspectRatio (p<0.0001, AUC=0.75), Non-sphericity Index (p<0.0001, AUC=0.75), Height/Width (p<0.0001, AUC=0.73), and SizeRatio (p<0.0001, AUC=0.73) as best among established descriptors, and Elongation (p<0.0001, AUC=0.71) and Flatness (p<0.0001, AUC=0.72) among Radiomics features. Radiomics Elongation correlated best with established Height/Width (R ²=0.52), whereas Radiomics Flatness correlated best with Ellipticity Index (R ²=0.54). Radiomics Sphericity correlated best with Undulation Index (R ²=0.65). Best Radiomics performers, Elongation and Flatness, were highly correlated descriptors (p<0.0001, R ²=0.75). In multivariate analysis, established descriptors (Height/Width, SizeRatio, Ellipticity Index; AUC=0.79) outperformed Radiomics features (Elongation, Maximum3Ddiameter; AUC=0.75).

CONCLUSION

Although recently introduced Radiomics analysis for aneurysm shape and size evaluation has the advantage of being an efficient operator independent methodology, it currently offers inferior rupture status discriminant performance compared with established descriptors. Future research is needed to extend the current Radiomics feature set to better capture aneurysm shape information.

A preliminary investigation of radiomics differences between ruptured and unruptured intracranial aneurysms

OBJECTIVES

Prediction of intracranial aneurysm rupture is important in the management of unruptured aneurysms. The application of radiomics in predicting aneurysm rupture remained largely unexplored. This study aims to evaluate the radiomics differences between ruptured and unruptured aneurysms and explore its potential use in predicting aneurysm rupture.

METHODS

One hundred twenty-two aneurysms were included in the study (93 unruptured). Morphological and radiomics features were extracted for each case. Statistical analysis was performed to identify significant features which were incorporated into prediction models constructed with a machine learning algorithm. To investigate the usefulness of radiomics features, three models were constructed and compared. The baseline model A was constructed with morphological features, while model B was constructed with addition of radiomics shape features and model C with more radiomics features. Multivariate analysis was performed for the ten most important variables in model C to identify independent risk factors. A simplified model based on independent risk factors was constructed for clinical use.

RESULTS

Five morphological features and 89 radiomics features were significantly associated with rupture. Model A, model B, and model C achieved the area under the receiver operating characteristic curve of 0.767, 0.807, and 0.879, respectively. Model C was significantly better than model A and model B (p < 0.001). Multivariate analysis identified two radiomics features which were used to construct the simplified model showing an AUROC of 0.876.

CONCLUSIONS

Radiomics signatures were different between ruptured and unruptured aneurysms. The use of radiomics features, especially texture features, may significantly improve rupture prediction performance.

KEY POINTS

• Significant radiomics differences exist between ruptured and unruptured intracranial aneurysms. • Radiomics shape features can significantly improve rupture prediction performance over conventional morphology-based prediction model. The inclusion of histogram and texture radiomics features can further improve the performance. • A simplified model with two variables achieved a similar level of performance as the more complex ones. Our prediction model can serve as a promising tool for the risk management of intracranial aneurysms.

Radiomic Model for Distinguishing Dissecting Aneurysms from Complicated Saccular Aneurysms on high-Resolution Magnetic Resonance Imaging

OBJECTIVE

To build radiomic model in differentiating dissecting aneurysm (DA) from complicated saccular aneurysm (SA) based on high-resolution magnetic resonance imaging (HR-MRI) through machine-learning algorithm.

METHODS

Overall, 851 radiomic features from 77 cases were retrospectively analyzed, and the ElasticNet algorithm was used to build the radiomic model. A clinico-radiological model using clinical features and conventional MRI findings was also built. An integrated model was then built by incorporating the radiomic model and clinico-radiological model. The diagnostic abilities of these models were evaluated using leave one out cross validation and quantified using the receiver operating characteristic (ROC) analysis. The diagnostic performance of radiologists was also evaluated for comparison.

RESULTS

Five features were used to form the radiomic model, which yielded an area under the ROC curve (AUC) of 0.912 (95 % CI 0.846-0.976), sensitivity of 0.852, and specificity of 0.861. The radiomic model achieved a better diagnostic performance than the clinico-radiological model (AUC=0.743, 95 % CI 0.623-0.862), integrated model (AUC=0.888, 95 % CI 0.811-0.965), and even many radiologists.

CONCLUSION

Radiomic features derived from HR-MRI can reliably be used to build a radiomic model for effectively differentiating between DA and complicated SA, and it can provide an objective basis for the selection of clinical treatment plan.

Predictive factors of incomplete aneurysm occlusion after endovascular treatment with the Pipeline embolization device

OBJECTIVE

The Pipeline embolization device (PED) is a routine choice for the endovascular treatment of select intracranial aneurysms. Its success is based on the high rates of aneurysm occlusion, followed by near-zero recanalization probability once occlusion has occurred. Therefore, identification of patient factors predictive of incomplete occlusion on the last angiographic follow-up is critical to its success.

METHODS

A multicenter retrospective cohort analysis was conducted on consecutive patients treated with a PED for unruptured aneurysms in 3 academic institutions in the US. Patients with angiographic follow-up were selected to identify the factors associated with incomplete occlusion.

RESULTS

Among all 3 participating institutions a total of 523 PED placement procedures were identified. There were 284 procedures for 316 aneurysms, which had radiographic follow-up and were included in this analysis (median age 58 years; female-to-male ratio 4.2:1). Complete occlusion (100% occlusion) was noted in 76.6% of aneurysms, whereas incomplete occlusion (≤ 99% occlusion) at last follow-up was identified in 23.4%. After accounting for factor collinearity and confounding, multivariable analysis identified older age (> 70 years; OR 4.46, 95% CI 2.30-8.65, p < 0.001); higher maximal diameter (≥ 15 mm; OR 3.29, 95% CI 1.43-7.55, p = 0.005); and fusiform morphology (OR 2.89, 95% CI 1.06-7.85, p = 0.038) to be independently associated with higher rates of incomplete occlusion at last follow-up. Thromboembolic complications were noted in 1.4% and hemorrhagic complications were found in 0.7% of procedures.

CONCLUSIONS

Incomplete aneurysm occlusion following placement of a PED was independently associated with age > 70 years, aneurysm diameter ≥ 15 mm, and fusiform morphology. Such predictive factors can be used to guide individualized treatment selection and counseling in patients undergoing cerebrovascular neurosurgery.

Bifurcation Configuration Is an Independent Risk Factor for Aneurysm Rupture Irrespective of Location

Background: Bifurcation and sidewall aneurysms have different rupture risks, but whether this difference comes from the location of the aneurysm is not clear. The objective of this study is to illustrate the rationality of ranking bifurcation configuration as an independent risk factor for aneurysm rupture.

Methods: Morphological features of 719 aneurysms (216 ruptured) were automatically extracted from a consecutive cohort of patients via PyRadiomics. Rupture risks and morphological features were compared between bifurcation and sidewall aneurysms, and lasso regression was applied to explore the morphological determinants for rupture in bifurcation and sidewall aneurysms. Rupture risks and morphological features of bifurcation aneurysms in different locations were analyzed. Multivariate regression was performed to explore the risk factors for aneurysm rupture.

Results: Twelve morphological features were automatically extracted from PyRadiomics implemented in Python. The rupture risks were higher in bifurcation aneurysms (P < 0.01), and morphological features Elongation and Flatness were much lower in ruptured bifurcation than sidewall aneurysms (P = 0.036, 0.011, respectively). Elongation and Flatness were the morphological determinants for rupture in bifurcation aneurysms, whereas Elongation and SphericalDisproportion were determinants for sidewall aneurysms. Different rupture risks and morphological features were found between sidewall and bifurcation aneurysms of the same location, and among bifurcation aneurysms of different locations. In multivariate regression, bifurcation configuration was an independent risk factor for aneurysm rupture (OR 3.007, 95% CI 1.752–5.248, P < 0.001).

Conclusions: Sidewall and bifurcation aneurysms and bifurcation aneurysms of different locations have different rupture risks and morphological features. Bifurcation configuration is an independent risk factor for aneurysm rupture irrespective of location.

Prediction of Aneurysm Stability Using a Machine Learning Model Based on PyRadiomics-Derived Morphological Features

Background and Purpose- Discrimination of the stability of intracranial aneurysms is critical for determining the treatment strategy, especially in small aneurysms. This study aims to evaluate the feasibility of applying machine learning for predicting aneurysm stability with radiomics-derived morphological features. Methods- Morphological features of 719 aneurysms were extracted from PyRadiomics, of which 420 aneurysms with Maximum3DDiameter ranging from 4 mm to 8 mm were enrolled for analysis. The stability of these aneurysms and other clinical characteristics were reviewed from the medical records. Based on the morphologies with/without clinical features, machine learning models were constructed and compared to define the morphological determinants and screen the optimal model for predicting aneurysm stability. The effect of clinical characteristics on the morphology of unstable aneurysms was analyzed. Results- Twelve morphological features were automatically extracted from PyRadiomics implemented in Python for each aneurysm. Lasso regression defined Flatness as the most important morphological feature to predict aneurysm stability, followed by SphericalDisproportion, Maximum2DDiameterSlice, and SurfaceArea. SurfaceArea (odds ratio [OR], 0.697; 95% CI, 0.476-0.998), SphericalDisproportion (OR, 1.730; 95% CI, 1.143-2.658), Flatness (OR, 0.584; 95% CI, 0.374-0.894), Hyperlipemia (OR, 2.410; 95% CI, 1.029-5.721), Multiplicity (OR, 0.182; 95% CI, 0.082-0.380), Location at middle cerebral artery (OR, 0.359; 95% CI, 0.134-0.902), and internal carotid artery (OR, 0.087; 95% CI, 0.030-0.211) were enrolled into the final prediction model. In terms of performance, the area under curve of the model reached 0.853 (95% CI, 0.767-0.940). For unstable aneurysms, Compactness1 (P=0.035), Compactness2 (P=0.036), Sphericity (P=0.035), and Flatness (P=0.010) were low, whereas SphericalDisproportion (P=0.034) was higher in patients with hypertension. Conclusions- Morphological features extracted from PyRadiomics can be used for aneurysm stratification. Flatness is the most important morphological determinant to predict aneurysm stability. Our model can be used to predict aneurysm stability. Unstable aneurysm is more irregular in patients with hypertension.

Effect of aneurysm morphologic parameters on occlusion rates following pipeline embolization

OBJECTIVE

Treatment failures with the use of Pipeline Embolization Device (PED) continue to be observed in up to 18% of patients in large case series. Adjunctive coiling and layering of multiple devices have been shown to improve occlusion rates; however, the optimal treatment strategy with the use of PED has not been established. The purpose of this study is to identify morphological characteristics predictive of treatment failure after PED.

PATIENT AND METHODS

A case control design was used to evaluate the association of aneurysm morphologic parameters with failure after PED placement. Retrospective analysis of patients undergoing PED for elective aneurysm treatment between 2014 and 2017 was performed. Patients who underwent PED placement with at least 12 months follow-up using conventional cerebral angiography were included for further review.

RESULTS

84 patients met inclusion criteria for further analysis. ten patients (11.9%) experienced treatment failure defined by retained flow within the aneurysm and of those eight patients (9.5%) required additional retreatment. On multivariate analysis decreasing aspect ratio and increasing neck width were significant parameters that predicted treatment failure.

CONCLUSION

Aneurysms with small aspect ratio and large neck width may be more likely to experience treatment failure after PED embolization. This subset of aneurysms may therefore benefit from adjunctive coiling to improve occlusion rates. Future prospective studies are needed to validate these findings.