Rupture-Related Features of Cerebral Arteriovenous Malformations and Their Utility in Predicting Hemorrhage.

BACKGROUND: Evaluating rupture risk in cerebral arteriovenous malformations currently lacks quantitative hemodynamic and angioarchitectural features necessary for predicting subsequent hemorrhage. We aimed to derive rupture-related hemodynamic and angioarchitectural features of arteriovenous malformations and construct an ensemble model for predicting subsequent hemorrhage. METHODS: This retrospective study included 3 data sets, as follows: training and test data sets comprising consecutive patients with untreated cerebral arteriovenous malformations who were admitted from January 2015 to June 2022 and a validation data set comprising patients with unruptured arteriovenous malformations who received conservative treatment between January 2009 and December 2014. We extracted rupture-related features and developed logistic regression (clinical features), decision tree (hemodynamic features), and support vector machine (angioarchitectural features) models. These 3 models were combined into an ensemble model using a weighted soft-voting strategy. The performance of the models in discriminating ruptured arteriovenous malformations and predicting subsequent hemorrhage was evaluated with confusion matrix-related metrics in the test and validation data sets. RESULTS: A total of 896 patients (mean±SD age, 28±14 years; 404 women) were evaluated, with 632, 158, and 106 patients in the training, test, and validation data sets, respectively. From the training set, 9 clinical, 10 hemodynamic, and 2912 pixel-based angioarchitectural features were extracted. A logistic regression model was built using 4 selected clinical features (age, nidus size, location, and venous aneurysm), whereas a decision-tree model was constructed from 4 hemodynamic features (outflow time, stasis index, cerebral blood flow, and outflow volume ratio). A support vector machine model was designed using 5 pixel-based angioarchitectural features. In the validation data set, the accuracy, sensitivity, specificity, and area under the curve of the ensemble model for predicting subsequent hemorrhages were 0.840, 0.889, 0.823, and 0.911, respectively. CONCLUSIONS: The ensemble model incorporating clinical, hemodynamic, and angioarchitectural features showed favorable performance in predicting subsequent hemorrhage of cerebral arteriovenous malformations.

Retrograde placement of flow diversion for the treatment of giant internal carotid artery aneurysm.

The use of flow diverters has been well-validated for the treatment of giant internal carotid artery aneurysms. However, in certain complex cases, the navigation of stent microcatheters across the neck may pose a relative challenge.1-3 In this technical video (video 1), we present the case of a patient in their 50s experiencing discomfort in the left eye. Angiography identified a giant aneurysm in the ophthalmic segment of the left internal carotid artery. Before seeking care at our institution, the patient had two interventional procedures, both unsuccessful due to difficulties in navigating the microcatheter past the aneurysm neck.4-5 In our management, after multiple unsuccessful anterograde attempts, we employed a retrograde strategy via the vertebral-basilar-posterior communicating artery route. This approach facilitated the successful deployment of the flow diverter and led to effective aneurysm embolization, underscoring the value of retrograde techniques for challenging cases.

Estimation of venous sinus pressure drop in patients with idiopathic intracranial hypertension using 4D-flow MRI.

OBJECTIVE: We aimed to explore a non-invasive estimate of pressure drop in patients who undergo venous sinus stenting to treat idiopathic intracranial hypertension (IIH). METHODS: This prospective study included 28 IIH patients scheduled for venous stenting. 4D-flow MRI was acquired 24-48 h before venous manometry. Manometry-obtained pressure drop (Mp) was dichotomized into low (Lp: 0-8 mmHg) and high (Hp: 8-30 mmHg) groups. Hemodynamic indices were compared between Lp and Hp. Trans-stenotic pressure drop was estimated by work-energy equation, simplified Bernoulli equation, vorticity magnitude, and velocity difference between inlet and outlet and was compared with Mp. Measurement agreement, correlation, and accuracy were evaluated using the κ coefficient, Pearson's r, and confusion matrix-derived accuracy. RESULTS: Among 28 patients (mean age 38.8 ± 12.7), 19 (67.9%) were female. Work-energy equation-estimated pressure drop (WEp) had strong correlation (r = 0.91, 95% confidence interval [CI]: 0.81-0.96, p < 0.001) and high agreement (intraclass correlation coefficient = 0.90, 95% CI: 0.78-0.95, p < 0.001) with Mp. WEp classified Lp and Hp with an accuracy of 0.96. The κ value between WEp and Mp was 0.92 (95% CI: 0.78-1.00). In the work-energy equation, the viscosity energy term (Ve) had the largest weights, and the ratio of Ve to the summation of the three energy terms was 0.93 ± 0.07. Ve had strong correlation with mVort (r = 0.93, 95% CI: 0.85-0.97, p < 0.001), and mean vorticity magnitude was significantly elevated in Hp compared to that in Lp (259.8 vs. 174.9 mL/s, p < 0.001). CONCLUSION: Trans-stenotic pressure drop in IIH can be estimated using the work-energy equation with favorable accuracy. KEY POINTS: • Trans-stenotic pressure drop in patients with idiopathic intracranial hypertension can be estimated accurately with the work-energy equation using the 4D-flow MRI full velocity field. • Compared with traditional venous sinus manometry, the 4D-flow MRI-derived pressure drop is totally non-invasive and cost-saving. • 4D-flow MRI may help neurointerventionalist to select IIH patients suitable for venous sinus stenting.

High-resolution magnetic resonance imaging-based radiomic features aid in selecting endovascular candidates among patients with cerebral venous sinus thrombosis.

OBJECTIVES: Cerebral venous sinus thrombosis (CVST) can cause sinus obstruction and stenosis, with potentially fatal consequences. High-resolution magnetic resonance imaging (HRMRI) can diagnose CVST qualitatively, although quantitative screening methods are lacking for patients refractory to anticoagulation therapy and who may benefit from endovascular treatment (EVT). Thus, in this study, we used radiomic features (RFs) extracted from HRMRI to build machine learning models to predict response to drug therapy and determine the appropriateness of EVT. MATERIALS AND METHODS: RFs were extracted from three-dimensional T1-weighted motion-sensitized driven equilibrium (MSDE), T2-weighted MSDE, T1-contrast, and T1-contrast MSDE sequences to build radiomic signatures and support vector machine (SVM) models for predicting the efficacy of standard drug therapy and the necessity of EVT. RESULTS: We retrospectively included 53 patients with CVST in a prospective cohort study, among whom 14 underwent EVT after standard drug therapy failed. Thirteen RFs were selected to construct the RF signature and CVST-SVM models. In the validation dataset, the sensitivity, specificity, and area under the curve performance for the RF signature model were 0.833, 0.937, and 0.977, respectively. The radiomic score was correlated with days from symptom onset, history of dyslipidemia, smoking, fibrin degradation product, and D-dimer levels. The sensitivity, specificity, and area under the curve for the CVST-SVM model in the validation set were 0.917, 0.969, and 0.992, respectively. CONCLUSIONS: The CVST-SVM model trained with RFs extracted from HRMRI outperformed the RF signature model and could aid physicians in predicting patient responses to drug treatment and identifying those who may require EVT.

Quantitative evaluation of the hemodynamic differences between ruptured and unruptured cerebral arteriovenous malformations using angiographic parametric imaging-derived radiomics features.

PURPOSE: Imaging features of cerebral arteriovenous malformations (AVMs) are mainly interpreted according to demographic and qualitative anatomical characteristics. This study aimed to use angiographic parametric imaging (API)-derived radiomics features to explore whether these features extracted from digital subtraction angiography (DSA) were associated with the hemorrhagic presentation of AVMs. METHODS: Patients with AVM were retrospectively evaluated. Among them, 80% were randomly assigned to a training dataset, and the remaining 20% were assigned to an independent test dataset. Radiomics features were extracted from DSA by API. Then, informative features were selected from radiomics features and clinical features using the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm. A model was constructed based on the selected features to classify the dichotomous hemorrhagic presentation in the training dataset. The model performance was evaluated in the test dataset with confusion matrix-related metrics. RESULTS: A total of 529 consecutive patients with AVMs between July 2011 and December 2020 were included in this study. After being selected by the LASSO algorithm and analyzed by multivariable logistic regression, three clinical features, namely, age (p = 0.01), nidus size (p < 0.001), and venous drainage patterns (p < 0.001), and four radiomics features were used to construct a model in the training dataset. On the independent test dataset, the model demonstrated a sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 0.852, 0.844, 0.881, 0.809, and 0.849, respectively. CONCLUSION: The radiomics features extracted from DSA by API could be potential indicators for the hemorrhagic presentation of AVMs.

Application of the Willis covered stent in the treatment of internal carotid artery blood blister-like aneurysms.

The optimal treatment for blood blister-like aneurysm (BBA) has not yet been determined, and BBA has a high recurrence rate after stent-assisted embolization. The purpose of the present study was to evaluate the safety and feasibility of patients with BBA rupture in the acute phase or patients with BBA who have recurrence after stent-assisted coil embolization. Eight patients (8 women, mean age 50.3 ± 3.7 years) who presented with ruptured BBA or recurrence BBA that had been treated by stent-assisted embolization (5 patients after primary treatment of stent-assisted embolization) were retrospectively reviewed. Clinical follow-up was performed at 1 year after endovascular treatment. All patients were successfully treated with the WCS, and immediate postoperative angiography showed that the aneurysms were completely isolated. The ophthalmic artery was covered by WCS in one patient; however, this patient did not show any clinical visual field or vision symptoms. Procedure-related complications such as aneurysm rupture, vasospasm, acute thrombosis, or thromboembolism did not occur in any case. All patients were followed up for 1 year after endovascular treatment, and they were in good condition without recurrence. One patient developed delayed bleeding at the right temporal lobe. All patients had good clinical prognosis (modified Rankin Scale score ≤ 2). WCS implantation may be a safe and feasible strategy for patients with BBA rupture in the acute phase and patients with BBA who have recurrence after stent-assisted coil embolization and is a promising option worth exploring.

Radiomics features on non-contrast-enhanced CT scan can precisely classify AVM-related hematomas from other spontaneous intraparenchymal hematoma types.

OBJECTIVE: To investigate the classification ability of quantitative radiomics features extracted on non-contrast-enhanced CT (NECT) image for discrimination of AVM-related hematomas from those caused by other etiologies. METHODS: Two hundred sixty-one cases with intraparenchymal hematomas underwent baseline CT scan between 2012 and 2017 in our center. Cases were split into a training dataset (n = 180) and a test dataset (n = 81). Hematoma types were dichotomized into two classes, namely, AVM-related hematomas (AVM-H) and hematomas caused by other etiologies. A total of 576 radiomics features of 6 feature groups were extracted from NECT. We applied 11 feature selection methods to select informative features from each feature group. Selected radiomics features and the clinical feature age were then used to fit machine learning classifiers. In combination of the 11 feature selection methods and 8 classifiers, we constructed 88 predictive models. Predictive models were evaluated and the optimal one was selected and evaluated. RESULTS: The selected radiomics model was RELF_Ada, which was trained with Adaboost classifier and features selected by Relief method. Cross-validated area under the curve (AUC) on training dataset was 0.988 and the relative standard deviation (RSD%) was 0.062. AUC on the test dataset was 0.957. Accuracy (ACC), sensitivity, specificity, positive prediction value (PPV), and negative predictive value (NPV) were 0.926, 0.889, 0.937, 0.800, and 0.967, respectively. CONCLUSIONS: Machine learning models with radiomics features extracted from NECT scan accurately discriminated AVM-related intraparenchymal hematomas from those caused by other etiologies. This technique provided a fast, non-invasive approach without use of contrast to diagnose this disease. KEY POINTS: • Radiomics features from non-contrast-enhanced CT accurately discriminated AVM-related hematomas from those caused by other etiologies. • AVM-related hematomas tended to be larger in diameter, coarser in texture, and more heterogeneous in composition. • Adaboost classifier is an efficient approach for analyzing radiomics features.

Parent artery sacrifice for ruptured aneurysms in acute and chronic phases: A systematic review.

BACKGROUND: Experience with respect to parent vessel sacrifice (PVS) for unclippable/uncoilable ruptured aneurysms is limited. OBJECTIVE: The aim of the present systematic review was to evaluate the risk of PVS for unclippable/uncoilable ruptured aneurysms. MATERIALS AND METHODS: The PUBMED and SCIENCEDIRECT databases were searched using "parent vessel occlusion OR parent artery occlusion" AND "acute subarachnoid hemorrhage" till December 27, 2015, and 1 journal was searched from November 1995 to April 2016 for relevant results. RESULTS: Out of a total of 19 eligible studies, 104 patients with 104 ruptured aneurysms were treated by PVS with or without bypass surgery. Unfavorable outcome [modified Rankin Score (mRS) 4-6] was reported in 14 (13.4%) acute phase patients, with a 9.6% mortality rate. Thirty (28.8%) patients developed ischemic complications and 3 (2.9%) developed bleeding complications. The complication rate was higher for PVS in the acute phase (38.0% vs. 12.0%; P= 0.015). The unfavorable clinical outcome was found to be significant in acute phase versus chronic phase (17.7% vs. 0%; P= 0.024). The risk of morbidity associated with distal vessel [posterior cerebral artery (PCA) + superior cerebellar artery (SCA) + posterior inferior cerebellar artery (PICA)] sacrifice was not lower than that associated with major vessel [internal carotid artery (ICA) + basilar artery (BA) + vertebral artery (VA)] sacrifice (P = 0.961). CONCLUSION: Complication and unfavorable outcome rates associated with PVS for acutely ruptured aneurysms are high. The risk of distal vessel sacrifice was not lower than major vessel sacrifice in the acute phase.

A systematic review of pipeline embolization device for giant intracranial aneurysms.

The experience with respect to the treatment of giant intracranial aneurysms with flow-diversion devices is limited. The aim of the present systematic review was to evaluate the effect of the pipeline embolization device (PED) on giant intracranial aneurysms. Eligible related articles were identified by searching the PubMed, Web of Science, Springer, ScienceDirect, and OVID databases using "giant aneurysm" and "pipeline" as the search items. The date of the last search was November 20, 2015. This systematic review adopted the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. In a total of 9 eligible studies with 200 patients and 215 aneurysms, 40 (18.6%) giant (aneurysm diameter >25mm) intracranial aneurysms treated with PED were analyzed. During a 6 to 34 month follow-up, complete occlusion was achieved in 23 (57.5%) cases. Seven patients (17.5%) developed intracranial hemorrhage, 5 developed ischemic attack (12.5%), and 13 (32.5%) developed a mass effect after PED treatment. The complication rate was 77.8% in PED for giant vertebrobasilar artery aneurysms. The cumulative mortality rate for giant paraclinoid carotid artery and middle cerebral artery aneurysms was 13.3% and increased up to 50% for giant vertebrobasilar artery aneurysms. The complete obliteration rate of PED for giant intracranial aneurysms was approximately 60%. Mass effect is the most mechanism of complications. Complication and mortality rates associated with PED for giant vertebrobasilar artery aneurysms are still extremely high.

Risk Score for Neurological Complications After Endovascular Treatment of Unruptured Intracranial Aneurysms.

BACKGROUND AND PURPOSE: Procedure-related neurological complications are common after endovascular treatment of unruptured intracranial aneurysms. We aimed to develop a score to quantify individual patient risk. METHODS: We retrospectively analyzed consecutive patients who underwent endovascular treatment for unruptured intracranial aneurysms between January 2012 and September 2015. After excluding those who lost to follow-up and those with fusiform unruptured intracranial aneurysms, included patients were randomly divided into a derivation group (60%) and a validation group (40%). A neurological complication was defined as any transient or permanent increase in the modified Rankin Scale score after aneurysm embolization. A risk score for neurological complications was derived from multivariable logistic regression analyses in the derivation group and validated in the validation group. RESULTS: Overall, 1060 patients were included (636 in the derivation group and 424 in the validation group). The incidence of neurological complications was 5.5% (95% confidence interval, 3.8%-7.4%). A 3-point risk score (S-C-C) was derived to predict neurological complications (size [≥10 mm=1], core areas [yes=1], and cerebral ischemic comorbidity [yes=1]). The incidence of neurological complications varied from 2.2% in 0-point patients to 25.0% in 3-point patients. The score demonstrated significant discrimination (C-statistic, 0.714; 95% confidence interval, 0.624-0.804) and calibration (McFadden R(2), 0.102) in the derivation group. Excellent prediction, discrimination, and calibration properties were reproduced in the validation group. CONCLUSIONS: One in 20 patients will develop neurological complications after endovascular treatment of unruptured intracranial aneurysms. The S-C-C score may be useful for predicting these adverse outcomes based on variables in daily practice.

Assessment of Risk of Aneurysmal Rupture in Patients with Normotensives, Controlled Hypertension, and Uncontrolled Hypertension.

BACKGROUND: The prevalence of hypertension in patients with intracranial aneurysms has been an increased concern, but it is not well understood if uncontrolled hypertension has impact on aneurysmal rupture. The aim of this study was to determine whether the risk of aneurysmal rupture is higher in uncontrolled hypertensive cohorts than in controlled hypertensive cohorts and normotensive cohorts. METHODS: We retrospectively analyzed the records and angiographies of 456 patients with aneurysms who were treated at our center between June 2013 and June 2014. Three groups of patients were included in the study following the ESH-ESC (European Society of Hypertension-European Society of Cardiology) 2013 guidelines: normotensive group (n = 229), controlled hypertension group (n = 127), and uncontrolled hypertension group (n = 100). Paired comparisons of these 3 groups were analyzed with the Nemenyi test. Multivariate logistic regression analysis was used to exclude the impact of possible confounding factors. RESULTS: The results of the univariate analysis showed that hypertension, smoking, and size of the aneurysms were significantly associated with intracranial aneurysmal rupture (P < .05). The multivariate logistic regression analysis containing clinical and aneurysmal characteristics showed that uncontrolled hypertension, smoking, and aneurysm size were statistically significant predictors of intracranial aneurysmal rupture (P < .05). The paired comparisons of 3 groups showed that the risk of rupture of intracranial aneurysms in the uncontrolled hypertension group was significantly greater than that in the normotensive group (P < .05) and in the controlled hypertension group (P < .05). CONCLUSIONS: Uncontrolled hypertension is associated with increased risk of rupture of intracranial aneurysms. Given that aneurysmal rupture is a potentially fatal-but preventable-complication, these findings are of clinical relevance.

Stent-assisted coiling of very small wide-necked intracranial aneurysms: Complications, anatomical results and clinical outcomes.

BACKGROUND AND OBJECTIVE: Treatment of very small (≤3mm) wide-necked intracranial aneurysms remains controversial, we investigated the efficacy and safety of stent-assisted coiling of such aneurysms. METHODS: From September 2008 to December 2012, 112 very small wide-necked intracranial aneurysms in 108 patients were embolized with stent-assisted coiling. We assessed the initial neurological conditions, complications and anatomic results. The follow-up results were evaluated with DSA and mRS. RESULTS: Stent deployment was successful in 104 of 108 procedures (96.3%). 11 complications (10.2%) occurred during procedures, including 5 events of aneurysm rupture, 3 events of thromboembolism. The rate of complication, rupture and thromboembolism was not statistically different between the ruptured and unruptured patients (P=0.452, P=0.369, P=1.000, respectively). The initial aneurysmal occlusion was Raymond scale (RS) 1 in 34 patients (31.5%), RS2 in 53 patients (49.1%), and RS3 in 21 patients (19.4%). 79 aneurysms were available for anatomic follow-up of 12-47 months, stable occlusion in 45 aneurysms (57.0%), progressive complete occlusion in 34 aneurysms (43.0%). 95 patients(88.0%) were available for a clinical follow-up of 12-52 months, 92 patients (96.8%) had favorable clinical outcomes (mRS ≤2), 3 patients (3.2%) had morbidity (mRS: 3-5). The morbidity was not statistically different between the ruptured and unruptured patients (P=1.000). CONCLUSIONS: Stent-assisted coiling of very small wide-necked intracranial aneurysms may be effective and safe. Because of low risk of rupture in such aneurysms, the coiling of unruptured such aneurysms must be selective. The long-term efficacy and safety of coiling such aneurysms remains to be determined in larger prospective series.

Enterprise stent-assisted coiling for wide-necked intracranial aneurysms during ultra-early (48hours) subarachnoid hemorrhage: a single-center experience in 59 consecutive patients.

BACKGROUND AND OBJECTIVE: Accumulated experience and improvement of stents dedicated to intracranial use have significantly widened the applicability of stent-assisted coiling (SAC) to ruptured wide-necked aneurysms. This retrospective study was designed to evaluate the safety and efficacy of SAC using the Enterprise stent for ruptured wide-necked intracranial aneurysms during ultra-early subarachnoid hemorrhage. METHOD: We reviewed data from 59 consecutive patients with ruptured wide-necked aneurysms who had SAC using the Enterprise stent performed within 48hours of onset. Data collected and analyzed included: patient demographics; morphologic features of the aneurysm; treatment results and follow-up results. Clinical outcomes were evaluated by modified Rankin Scale (mRS). RESULTS: In all 59 cases, SAC using the Enterprise stent was performed successfully, with no significant technical difficulties. Initial angiographic results were: complete occlusion in 38 cases; near occlusion in 17; and partial occlusion in four. Angiographic follow-up of 48 patients showed that 46 (95.8%) remained stable or improved, without regrowth, while regrowth was imaged in two patients. Medium-term clinical follow-up of 54 patients (mean, 26.9months) showed that 88.9% had a good outcome (mRS: 0 in 34; 1 in eight; and 2 in six), and 11.1% poor outcomes (mRS: 3 in four; and 4 in two). CONCLUSION: Enterprise SAC is a safe and viable option for treatment of ruptured wide-necked aneurysms within 48hours of ictus.

Impact of hypertension and smoking on the rupture of intracranial aneurysms and their joint effect.

BACKGROUND: In general population, the prevalence of intracranial aneurysm reaches as high as three percent. The goal of the study was to analyze retrospectively the independent risk factors for the rupture of intracranial aneurysms and their joint effect. METHODS: The records and angiographies of continuous 519 intracranial aneurysm patients treated at our center between February 2013 and July 2014 were retrospectively analyzed. Ruptured group and unruptured group were included in the study according to their clinical and imaging information. Univariate analysis and multivariate logistic regression analysis was used to identified independent risk factors for the rupture of intracranial aneurysms. We assessed the joint effect of independent risk factors for the rupture of intracranial aneurysms with an additional logistic regression analysis. RESULTS: The results of multivariate analysis show that hypertension (odds ratio [OR], 1.51; 95% confidence interval [CI], 1.05-2.18) and smoking (odds ratio [OR], 1.57; 95% confidence interval [CI], 1.06-2.33) were independent risk factors for rupture of intracranial aneurysms. The joint risk of hypertension and smoking was higher (OR, 2.28; 95% CI, 1.29-4.02) than the risks of hypertension (OR, 1.74; 95% CI, 1.11-2.72) and smoking (OR, 1.86; 95% CI, 1.05-3.29) independently. CONCLUSIONS: Hypertension and smoking increase of the rupture risk of intracranial aneurysms. And the joint risk of hypertension and smoking was higher than the risks of hypertension and smoking independently.

Onyx embolization of cavernous sinus dural arteriovenous fistulas via direct transorbital puncture under the guidance of three-dimensional reconstructed skull image (reports of six cases).

BACKGROUND: Because of complex angioarchitecture, the transarterial or venous pathway is not feasible for some cavernous sinus dural arteriovenous fistulas (CS DAVFs). We present six cases in which onyx embolization of a CS DAVFs was made possible through direct transorbital puncture. METHODS: In the present study, all patients were penetrated through one third of the medial-lateral of the inferior orbital rim under the guidance of fluoroscopy superimposed on the three-dimensional reconstructed skull image to complete embolization (onyx with or without coils). The records of patient demographics, clinical manifestation, fistula features, procedures, clinical outcome and angiographic outcome were reviewed and analyzed. RESULTS: In our series of six patients, the immediate angiographic result showed complete occlusion in all patients. The six patients experienced retrobulbarhematoma and eye swelling right after embolization, while the swelling significantly subsided after 3-5 days of conservative treatment. During the postoperative angiography and clinical follow-up (4-10 months), one of the patients had decreased visual acuity; the other five patients did not have neurological dysfunction. CONCLUSIONS: Onyx embolization via direct transorbital puncture provides a method to be considered to treat CS DAVFs when the conventional transvenous approaches are inaccessible.

An MRI radiomics approach to discriminate haemorrhage-prone intracranial tumours before stereotactic biopsy.

PURPOSE: To explore imaging biomarkers predictive of intratumoral haemorrhage for lesions intended for elective stereotactic biopsy. METHOD: This study included a retrospective cohort of 143 patients with 175 intracranial lesions intended for stereotactic biopsy. All the lesions were randomly split into a training dataset ( n =121) and a test dataset ( n =54) at a ratio of 7:3. Thirty-four lesions were defined as "hemorrhage-prone tumors" as haemorrhage occurred between initial diagnostic MRI acquisition and the scheduled biopsy procedure. Radiomics features were extracted from the contrast-enhanced T1 Weighted Imaging and T2 Weighted Imaging images. Features informative of haemorrhage were then selected by the LASSO algorithm, and an Support Vector Machine model was built with selected features. The Support Vector Machine model was further simplified by discarding features with low importance and calculating them using a "permutation importance" method. The model's performance was evaluated with confusion matrix-derived metrics and area under curve (AUC) values on the independent test dataset. RESULTS: Nine radiomics features were selected as haemorrhage-related features of intracranial tumours by the LASSO algorithm. The simplified model's sensitivity, specificity, accuracy, and AUC reached 0.909, 0.930, 0.926, and 0.949 (95% CI: 0.865-1.000) on the test dataset in the discrimination of "hemorrhage-prone tumors". The permutation method rated feature "T2_gradient_firstorder_10Percentile" as the most important, the absence of which decreased the model's accuracy by 10.9%. CONCLUSION: Radiomics features extracted on contrast-enhanced T1 Weighted Imaging and T2 Weighted Imaging sequences were predictive of future haemorrhage of intracranial tumours with favourable accuracy. This model may assist in the arrangement of biopsy procedures and the selection of target lesions in patients with multiple lesions.

Prediction of Venous Trans-Stenotic Pressure Gradient Using Shape Features Derived From Magnetic Resonance Venography in Idiopathic Intracranial Hypertension Patients.

OBJECTIVE: Idiopathic intracranial hypertension (IIH) is a condition of unknown etiology associated with venous sinus stenosis. This study aimed to develop a magnetic resonance venography (MRV)-based radiomics model for predicting a high trans-stenotic pressure gradient (TPG) in IIH patients diagnosed with venous sinus stenosis. MATERIALS AND METHODS: This retrospective study included 105 IIH patients (median age [interquartile range], 35 years [27-42 years]; female:male, 82:23) who underwent MRV and catheter venography complemented by venous manometry. Contrast enhanced-MRV was conducted under 1.5 Tesla system, and the images were reconstructed using a standard algorithm. Shape features were derived from MRV images via the PyRadiomics package and selected by utilizing the least absolute shrinkage and selection operator (LASSO) method. A radiomics score for predicting high TPG (≥ 8 mmHg) in IIH patients was formulated using multivariable logistic regression; its discrimination performance was assessed using the area under the receiver operating characteristic curve (AUROC). A nomogram was constructed by incorporating the radiomics scores and clinical features. RESULTS: Data from 105 patients were randomly divided into two distinct datasets for model training (n = 73; 50 and 23 with and without high TPG, respectively) and testing (n = 32; 22 and 10 with and without high TPG, respectively). Three informative shape features were identified in the training datasets: least axis length, sphericity, and maximum three-dimensional diameter. The radiomics score for predicting high TPG in IIH patients demonstrated an AUROC of 0.906 (95% confidence interval, 0.836-0.976) in the training dataset and 0.877 (95% confidence interval, 0.755-0.999) in the test dataset. The nomogram showed good calibration. CONCLUSION: Our study presents the feasibility of a novel model for predicting high TPG in IIH patients using radiomics analysis of noninvasive MRV-based shape features. This information may aid clinicians in identifying patients who may benefit from stenting.

Predicting postinterventional rupture of intracranial aneurysms using arteriography-derived radiomic features after pipeline embolization.

Background and purpose: Postinterventional rupture of intracranial aneurysms (IAs) remains a severe complication after flow diverter treatment. However, potential hemodynamic mechanisms underlying independent predictors for postinterventional rupture of IAs remain unclear. In this study, we employed arteriography-derived radiomic features to predict this complication. Methods: We included 64 patients who underwent pipeline flow diversion for intracranial aneurysms, distinguishing between 16 patients who experienced postinterventional rupture and 48 who did not. We performed propensity score matching based on clinical and morphological factors to match these patients with 48 patients with postinterventional unruptured IAs at a 1:3 ratio. Postinterventional digital subtraction angiography were used to create five arteriography-derived perfusion parameter maps and then radiomics features were obtained from each map. Informative features were selected through the least absolute shrinkage and selection operator method with five-fold cross-validation. Subsequently, radiomics scores were formulated to predict the occurrence of postinterventional IA ruptures. Prediction performance was evaluated with the training and test datasets using area under the curve (AUC) and confusion matrix-derived metrics. Results: Overall, 1,459 radiomics features were obtained, and six were selected. The resulting radiomics scores had high efficacy in distinguishing the postinterventional rupture group. The AUC and Youden index were 0.912 (95% confidence interval: 0.767-1.000) and 0.847 for the training dataset, respectively, and 0.938 (95% confidence interval, 0.806-1.000) and 0.800 for the testing dataset, respectively. Conclusion: Radiomics scores generated using arteriography-derived radiomic features effectively predicted postinterventional IA ruptures and may aid in differentiating IAs at high risk of postinterventional rupture.

Could the types of paraclinoid aneurysm be used as a criterion in choosing endovascular treatment? Neuro-radiologists' view.

BACKGROUND: The type of paraclinoid aneurysm has been used to decide management methods. Our aim was to assess the relation of the types of paraclinoid aneurysms and outcomes after endovascular treatment and the efficiency of present endovascular techniques. METHODS: A retrospective analysis was performed on patients with saccular paraclinoid aneurysms that had more than 6 months of angiographic follow-up or recurrence within this period after endovascular treatment from January 2009 to December 2010. Paraclinoid aneurysms were classified into two types and then further into four subtypes by a modified classification method. A classification-based microcatheter shaping method was used in the procedure. The significant risk factors of angiographic results were determined through correlation analysis and logistic regression analysis by SPSS 17.0. RESULTS: There were 64 aneurysms in 56 patients; 28 aneurysms belonged to Type I, while 36 were Type II. A total of 12 aneurysms were managed with coil embolization, and 52 with stent-assisted coiling technique. Our classification-based microcatheter shaping method was successful in all cases. Coil protrusion happened in two cases without severe complications. Recurrence were found in 13 (20.3 %) aneurysms followed up at 12.42 ± 3.78 (mean±SD) months after treatment. The correlation between aneurysm types and immediate angiographic result or follow-up angiographic results did not reach statistical significance. Aneurysm types were not the risk factor of recurrence. CONCLUSIONS: The types of paraclinoid aneurysm had not been significant correlated with outcomes of endovascular treatment. Fundus size was the significant risk factor of recurrence after endovascular treatment. A classification-based microcatheter shaping method may be used in endovascular treatment paraclinoid aneurysms. The present endovascular techniques are safe and effective.