The Role of Long Noncoding RNAs in Vascular Smooth Muscle Cell Phenotype and the Pathogenesis of Cardiovascular and Cerebrovascular Aneurysms.

ABSTRACT: Aneurysms are localized dilations of blood vessels, which can expand to 50% of the original diameter. They are more common in cardiovascular and cerebrovascular vessels. Rupture is one of the most dangerous complications. The pathophysiology of aneurysms is complex and diverse, often associated with progressive vessel wall dysfunction resulting from vascular smooth muscle cell death and abnormal extracellular matrix synthesis and degradation. Multiple studies have shown that long noncoding RNAs (lncRNAs) play a significant role in the progression of cardiovascular and cerebrovascular diseases. Therefore, it is necessary to find and summarize them. LncRNAs control gene expression and disease progression by regulating target mRNA or miRNA and are biomarkers for the diagnosis and prognosis of aneurysmal cardiovascular and cerebrovascular diseases. This review explores the role, mechanism, and clinical value of lncRNAs in aneurysms, providing new insights for a deeper understanding of the pathogenesis of cardiovascular and cerebrovascular aneurysms.

Quantifying irregular pulsation of intracranial aneurysms using 4D-CTA.

Recent studies have suggested that irregular pulsation of intracranial aneurysm during the cardiac cycle may be potentially associated with aneurysm rupture risk. However, there is a lack of quantification method for irregular pulsations. This study aims to quantify irregular pulsations by the displacement and strain distribution of the intracranial aneurysm surface during the cardiac cycle using four-dimensional CT angiographic image data. Four-dimensional CT angiography was performed in 8 patients. The image data of a cardiac cycle was divided into approximately 20 phases, and irregular pulsations were detected in four intracranial aneurysms by visual observation, and then the displacement and strain of the intracranial aneurysm was quantified using coherent point drift and finite element method. The displacement and strain were compared between aneurysms with irregular and normal pulsations in two different ways (total and stepwise). The stepwise first principal strain was significantly higher in aneurysms with irregular than normal pulsations (0.20±0.01 vs 0.16±0.02, p=0.033). It was found that the irregular pulsations in intracranial aneurysms usually occur during the consecutive ascending or descending phase of volume changes during the cardiac cycle. In addition, no statistically significant difference was found in the aneurysm volume changes over the cardiac cycle between the two groups. Our method can successfully quantify the displacement and strain changes in the intracranial aneurysm during the cardiac cycle, which may be proven to be a useful tool to quantify intracranial aneurysm deformability and aid in aneurysm rupture risk assessment.

On flow fluctuations in ruptured and unruptured intracranial aneurysms: resolved numerical study.

Flow fluctuations have emerged as a promising hemodynamic metric for understanding of hemodynamics in intracranial aneurysms. Several investigations have reported flow instabilities using numerical tools. In this study, the occurrence of flow fluctuations is investigated using either Newtonian or non-Newtonian fluid models in five patient-specific intracranial aneurysms using high-resolution lattice Boltzmann simulation methods. Flow instabilities are quantified by computing power spectral density, proper orthogonal decomposition, and fluctuating kinetic energy of velocity fluctuations. Our simulations reveal substantial flow instabilities in two of the ruptured aneurysms, where the pulsatile inflow through the neck leads to hydrodynamic instability, particularly around the rupture position, throughout the entire cardiac cycle. In other monitoring points, the flow instability is primarily observed during the deceleration phase; typically, the fluctuations begin just after peak systole, gradually decay, and the flow returns to its original, laminar pulsatile state during diastole. Additionally, we assess the rheological impact on flow dynamics. The disparity between Newtonian and non-Newtonian outcomes remains minimal in unruptured aneurysms, with less than a 5% difference in key metrics. However, in ruptured cases, adopting a non-Newtonian model yields a substantial increase in the fluctuations within the aneurysm sac, with up to a 30% higher fluctuating kinetic energy compared to the Newtonian model. The study highlights the importance of using appropriate high-resolution simulations and non-Newtonian models to capture flow fluctuation characteristics that may be critical for assessing aneurysm rupture risk.

Hemodynamic differences determining rupture and non-rupture in middle cerebral aneurysms after growth.

BACKGROUND AND PURPOSE: Intracranial aneurysm growth is a significant risk factor for rupture; however, a few aneurysms remain unruptured for long periods, even after growth. Here, we identified hemodynamic features associated with aneurysmal rupture after growth. MATERIALS AND METHODS: We analyzed nine middle cerebral artery aneurysms that grew during the follow-up period using computational fluid dynamics analysis. Growth patterns of the middle cerebral artery aneurysms were divided into homothetic growth (Type 1), de novo bleb formation (Type 2), and bleb enlargement (Type 3). Hemodynamic parameters of the four ruptured aneurysms after growth were compared with those of the five unruptured aneurysms. RESULTS: Among nine aneurysms (78%), seven were Type 1, one was Type 2, and one was Type 3. Three (43%) Type 1 aneurysms ruptured after growth. Maximum oscillatory shear index after aneurysmal growth was significantly higher in ruptured Type 1 cases than in unruptured Type 1 cases (ruptured vs. unruptured: 0.455 ± 0.007 vs. 0.319 ± 0.042, p = 0.003). In Type 1 cases, a newly emerged high-oscillatory shear index area was frequently associated with rupture, indicating a rupture point. Aneurysm growth was observed in the direction of the high-pressure difference area before enlargement. In Types 2 and 3 aneurysms, the maximum oscillatory shear index decreased slightly, however, the pressure difference values remain unchanged. In Type 3 aneruysm, the maximum OSI and PD values remained unchanged. CONCLUSIONS: This study suggests that hemodynamic variations and growth pattern changes are crucial in rupture risk determination using computational fluid dynamics analysis. High-pressure difference areas may predict aneurysm enlargement direction. Additionally, high maximum oscillatory shear index values after enlargement in cases with homothetic growth patterns were potential rupture risk factors.

Virtual flow diverter deployment and embedding for hemodynamic simulations.

Flow-diverter stents offer clinicians an effective solution for treating intracranial aneurysms, especially in cases where other devices may be unsuitable. However, strongly deviating success rates among different centres, manufacturers, and aneurysm phenotypes highlight the need for better in-situ studies of these devices. To support research in this area, virtual stenting algorithms have been proposed that, combined with computational fluid dynamics, provide insights into the hemodynamic alterations induced by the device. Yet, many existing algorithms rely on uncertain parameters, such as the forces applied during operation, fail to predict the length of the device after deployment, or lack robust validation steps, raising concerns about their reliability. Therefore, we developed a robust deployment technique that builds upon the geometrical features of the vessel and includes advancements from previous works. The algorithm is detailed and validated against literature examples, in-vitro experiments, and patient data, achieving a mean angular error below 5° in the latter. Furthermore, we describe and demonstrate how the deployed device can be embedded in a computational mesh using open-source tools and anisotropic meshing routines.

Patient-specific arterial wall generation for intracranial aneurysms with a variable and a near realistic vessel wall thickness for FSI studies.

BACKGROUND AND OBJECTIVE: Imaging methodologies such as, computed tomography (CT) aid in three-dimensional (3D) reconstruction of patient-specific aneurysms. The radiological data is useful in understanding their location, shape, size, and disease progression. However, there are serious impediments in discerning the blood vessel wall thickness due to limitations in the current imaging modalities. This further restricts the ability to perform high-fidelity fluid structure interaction (FSI) studies for an accurate assessment of rupture risk. FSI studies would require the arterial wall mesh to be generated to determine realistic maximum allowable wall stresses by performing coupled calculations for the hemodynamic forces with the arterial walls. METHODS: In the present study, a novel methodology is developed to geometrically model variable vessel wall thickness for the lumen isosurface extracted from CT scan slices of patient-specific aneurysms based on clinical and histopathological inputs. FSI simulations are carried out with the reconstructed models to assess the importance of near realistic wall thickness model on rupture risk predictions. RESULTS: During surgery, clinicians often observe translucent vessel walls, indicating the presence of thin regions. The need to generate variable vessel wall thickness model, that embodies the wall thickness gradation, is closer to such clinical observations. Hence, corresponding FSI simulations performed can improve clinical outcomes. Considerable differences in the magnitude of instantaneous wall shear stresses and von Mises stresses in the walls of the aneurysm was observed between a uniform wall thickness and a variable wall thickness model. CONCLUSION: In the present study, a variable vessel wall thickness generation algorithm is implemented. It was shown that, a realistic wall thickness modeling is necessary for an accurate prediction of the shear stresses on the wall as well as von Mises stresses in the wall. FSI simulations are performed to demonstrate the utility of variable wall thickness modeling.

Turbulent blood flow in a cerebral artery with an aneurysm.

Unruptured intracranial aneurysms are common in the general population, and many uncertainties remain when predicting rupture risks and treatment outcomes. One of the cutting-edge tools used to investigate this condition is computational fluid dynamics (CFD). However, CFD is not yet mature enough to guide the clinical management of this disease. In addition, recent studies have reported significant flow instabilities when refined numerical methods are used. Questions remain as to how to properly simulate and evaluate this flow, and whether these instabilities are really turbulence. The purpose of the present study is to evaluate the impact of the simulation setup on the results and investigate the occurrence of turbulence in a cerebral artery with an aneurysm. For this purpose, direct numerical simulations were performed with up to 200 cardiac cycles and with data sampling rates of up to 100,000 times per cardiac cycle. Through phase-averaging or triple decomposition, the contributions of turbulence and of laminar pulsatile waves to the velocity, pressure and wall shear stress fluctuations were distinguished. For example, the commonly used oscillatory shear index was found to be closely related to the laminar waves introduced at the inlet, rather than turbulence. The turbulence energy cascade was evaluated through energy spectrum estimates, revealing that, despite the low flow rates and Reynolds number, the flow is turbulent near the aneurysm. Phase-averaging was shown to be an approach that can help researchers better understand this flow, although the results are highly dependent on simulation setup and post-processing choices.

On the use of steady flow rates for approximating flow instabilities and vibrations in intracranial aneurysms.

Recent computational and experimental studies of intracranial aneurysms have revealed potential mechanisms of aneurysm bruits and murmurs, driven by flow instabilities rather than by stable pulsatile flow. Some of these studies have been conducted under the assumption of constant flow rate (steady flow); however the validity of this assumption has not been evaluated for high-frequency flow instability, or vibrations from fluid-structure interaction (FSI) simulations. We evaluated the time-averaged wall shear stress, flow instability and vibration amplitude of steady flow simulations, performed at both cycle-averaged and peak-systolic flow rates, and compared these to recent pulsatile FSI simulations. Wall shear stress fields of pulsatile flow (time-averaged and peak values) were well-approximated by the respective steady-flow FSI simulations, and the spatial distribution and frequency content of flow instability and vibrations were reasonably approximated by the steady flow simulations at peak-systolic flow rates. However, the level of flow instability and vibration was generally over-predicted by the steady flow simulations at peak-systolic flow rates as flow remained unstable for longer than in the pulsatile simulation, while no flow instability was detected for steady flow at cycle-averaged flow rates. Additionally, the amplitude of flow instability and vibration fluctuated considerably in the steady flow simulations, while the pulsatile simulations exhibited consistent vibration amplitudes (less than 10 % variation at peak systole between cycles). Finally, steady flow simulations at peak-systolic conditions required 2-3x more compute time than the pulsatile simulations for the same time duration. Therefore, we recommend using pulsatile flow simulations when investigating vibrations and flow instabilities.

Description of the local hemodynamic environment in intracranial aneurysm wall subdivisions.

Intracranial aneurysms (IAs) pose severe health risks influenced by hemodynamics. This study focuses on the intricate characterization of hemodynamic conditions within the IA walls and their influence on bleb development, aiming to enhance understanding of aneurysm stability and the risk of rupture. The methods emphasized utilizing a comprehensive dataset of 359 IAs and 213 IA blebs from 268 patients to reconstruct patient-specific vascular models, analyzing blood flow using finite element methods to solve the unsteady Navier-Stokes equations, the segmentation of aneurysm wall subregions and the hemodynamic metrics wall shear stress (WSS), its metrics, and the critical points in WSS fields were computed and analyzed across different aneurysm subregions defined by saccular, streamwise, and topographical divisions. The results revealed significant variations in these metrics, correlating distinct hemodynamic environments with wall features on the aneurysm walls, such as bleb formation. Critical findings indicated that regions with low WSS and high OSI, particularly in the body and central regions of aneurysms, are prone to conditions that promote bleb formation. Conversely, areas exposed to high WSS and positive divergence, like the aneurysm neck, inflow, and outflow regions, exhibited a different but substantial risk profile for bleb development, influenced by flow impingements and convergences. These insights highlight the complexity of aneurysm behavior, suggesting that both high and low-shear environments can contribute to aneurysm pathology through distinct mechanisms.

Stent-to-vessel diameter ratio is associated with in-stent stenosis after flow-diversion treatment of intracranial aneurysms.

BACKGROUND AND PURPOSE: Flow-diversion treatment for intracranial aneurysms has been associated with the development of in-stent stenosis (ISS) for unclear reasons. We assess whether the size of the stent relative to that of the vessel (the stent-to-vessel diameter ratio, or SVR) may be predictive of the development of ISS after treatment with flow diverters. METHODS: We retrospectively reviewed patients with unruptured intracranial aneurysms who underwent flow-diversion treatment using either the Pipeline or Tubridge embolization device from September 2018 to September 2022. The relationship between SVR and ISS was analyzed. Multiple logistic regression models were used to determine the significant predictors. RESULTS: A total of 458 patients with 481 aneurysms were included. In a mean angiographic follow-up of 10.73 ± 3.97 months, ISS was detected in 68 cases (14.1 %). After adjusting for candidate variables, a higher distal SVR (DSVR) was associated with an increased risk of ISS (adjusted odds ratio [aOR] = 3.420, 95 % confidence interval [CI] = 1.182 - 9.889, p = 0.023). We conducted a subgroup analysis of the two different flow diverters to assess the effects of their individual characteristics. Our results showed a significant association between the DSVR and the incidence of ISS in both the Pipeline (aOR = 4.033, 95 % CI = 1.156-14.072, p = 0.029) and Tubridge groups (aOR = 11.981, 95 % CI=1.005-142.774, p = 0.049). CONCLUSION: A higher DSVR was associated with an increased risk of ISS. This may help neurointerventionalists select an appropriate stent size when conducting flow-diversion treatment for intracranial aneurysms.

A multidimensional pre-operative planning method of unruptured vertebral artery dissecting aneurysms using three-dimensional AWE mapping and hemodynamic simulation.

OBJECTIVE: High-resolution magnetic resonance imaging (HR-MRI) can provide valuable insights into the evaluation of vascular pathological conditions, and 3D digital subtraction angiography (3D-DSA) offers clear visualization of the vascular morphology and hemodynamics. This study aimed to investigate the potential of a multimodal method to treat unruptured vertebral artery dissection aneurysms (u-VADAs) by fusing image data from HR-MRI and 3D-DSA. METHODS: This observational study enrolled 5 patients diagnosed with u-VADAs, who were scheduled for interventional treatment. The image data of HR-MRI and 3D-DSA were merged by geometry software, resulting in a multimodal model. Quantified values of aneurysm wall enhancement (AWE), wall shear stress (WSS), neck velocity, inflow volume, intra-stent flow velocity (ISvelocity), and intra-aneurysmal velocity (IAvelocity) were calculated from the multimodal method. RESULTS: We found the actual lengths of u-VADAs in the multimodal model were longer than the 3D-DSA model. We formulated surgical plannings based on the WSS, IA velocity, and neck velocity. The post-operative value of IAvelocity, neck velocity, and follow-up quantified values of AWE were decreased compared with the pre-operative condition. After that, u-VADAs were complete occlusion in four patients and near-complete occlusion in one patient during the 6th-month follow-up after surgery. CONCLUSION: The multidimensional method combining HR-MRI with 3D-DSA may provide more valuable information for treating VADAs, with the potential to develop effective surgical planning.

Statistical evaluation of measured biomechanical properties of human brain aneurysm samples.

Background and purpose:

Human brain aneurysms may often prove fatal if not re­cognized in time and treated accordingly. The understanding of development and rupture of aneurysms can significantly be improved by the application of numerical modelling, which in turn, requires the knowledge of mechanical properties of vessel wall. This study aims to identify assumed differences with respect to age, sex, spatial orientation, and rupture by utilizing detailed statistical analysis of uniaxial tensile measurements of human brain aneurysm samples, performed by the authors in a previous project.

At surgery of 42 patients, aneu­rysm fundi were cut distally to the clip. In each case, depending on size, varying number of stripes (altogether 88) were prepared and uniaxial stress-strain measurements were performed. Quantities related to the capacity, energy absorption or stiffness were determined and statistically analysed.

The number of specimens in the aneurysm sample was sufficient to establish statistical differences with respect to sex and rupture (p<0.05). No significant differences were detected in orientation, though higher values of stresses and deformations were ob­tained in the circumferential direction com­pared to the meridional direction. 

Significant differences bet­ween sexes with respect to ultimate deformations were demonstrated according to expectation, and the hypothesis on equality of energy capacity could be supported. Similarity of curves with respect to specimen orientation was also observed and ruptured aneurysm sacs tended to be smaller in size. It seems that differences and trends described in this paper are realistic and need to be applied in numerical modelling.

Distribution of rupture sites and blebs on intracranial aneurysm walls suggests distinct rupture patterns in ACom and MCA aneurysms.

The mechanisms behind intracranial aneurysm formation and rupture are not fully understood, with factors such as location, patient demographics, and hemodynamics playing a role. Additionally, the significance of anatomical features like blebs in ruptures is debated. This highlights the necessity for comprehensive research that combines patient-specific risk factors with a detailed analysis of local hemodynamic characteristics at bleb and rupture sites. Our study analyzed 359 intracranial aneurysms from 268 patients, reconstructing patient-specific models for hemodynamic simulations based on 3D rotational angiographic images and intraoperative videos. We identified aneurysm subregions and delineated rupture sites, characterizing blebs and their regional overlap, employing statistical comparisons across demographics, and other risk factors. This work identifies patterns in aneurysm rupture sites, predominantly at the dome, with variations across patient demographics. Hypertensive and anterior communicating artery (ACom) aneurysms showed specific rupture patterns and bleb associations, indicating two pathways: high-flow in ACom with thin blebs at impingement sites and low-flow, oscillatory conditions in middle cerebral artery (MCA) aneurysms fostering thick blebs. Bleb characteristics varied with gender, age, and smoking, linking rupture risks to hemodynamic factors and patient profiles. These insights enhance understanding of the hemodynamic mechanisms leading to rupture events. This analysis elucidates the role of localized hemodynamics in intracranial aneurysm rupture, challenging the emphasis on location by revealing how flow variations influence stability and risk. We identify two pathways to wall failure-high-flow and low-flow conditions-highlighting the complexity of aneurysm behavior. Additionally, this research advances our knowledge of how inherent patient-specific characteristics impact these processes, which need further investigation.

Evaluation of Hemodynamic Alterations after Flow Diverter Placement using the AneurysmFlowTM tool.

Background: AneurysmFlow (Phillips Healthcare) is the flow measurement tool, utilizing an optical flow-based algorithm from DSA, lacks sufficient published studies. This study aimed to assess the significance of flow velocity changes and the Mean Aneurysm Flow Amplitude (MAFA) ratio in evaluating outcomes following flow-diverting treatments. Methods: Between June 2021 and October 2022, 41 patients with 42 aneurysms underwent FDS treatment with AneurysmFlow measu-rement at the Bach Mai Radiology Center. Results: The tool achieved a 90.5% success rate in 38 out of 42 patients. Most aneurysms (89.5%) were small to medium-sized (<10 mm), and a decrease in flow velocity post-stent deployment was ob-served in 78.9% of cases. Conversely, 21.1% showed increased flow, mainly in aneurysms smaller than 5 mm. No significant association was found between flow changes or MAFA ratio and aneurysm size characteristics. Twenty-two patients (59.5%) underwent re-examination at 6 months, revealing no correlation in MAFA ratio between completely and incompletely occluded aneurysms. Conclusions: Our current investigation, primarily centered on small and medium-sized aneurysms, did not uncover any link between quantitative flow changes assessed using the AneurysmFlow software and the occlusion status of aneurysms at the 6-month follow-up post-flow diverter treatment. Larger case series with extended follow-up imaging are necessary to further explore these findings.

Effects of induced arterial hypertension for vasospasm on unruptured and unsecured cerebral aneurysms (growth and rupture). A retrospective case-control study.

OBJECTIVES: Unruptured cerebral aneurysms (UCAs) often coexist with the ruptured one but are typically left unsecured during the weeks following aneurysmal subarachnoid hemorrhage (aSAH). We compared the rate of UCAs rupture or volume growth (≥5 mm3) between patients exposed to induced arterial hypertension (iHTN) for vasospasm and those not exposed (control group). MATERIALS AND METHODS: From 2013 to 2021, we retrospectively included consecutive adult patients with aSAH who had ≥1 UCA. Custom software for digital subtraction angiography (DSA) image analysis characterized UCAs volume, going beyond merely considering UCAs long axis. RESULTS: We analyzed 118 patients (180 UCAs): 45 in the iHTN group (64 UCAs) and 73 in the control group (116 UCAs). Systolic blood pressure in the iHTN group was significantly higher than in the control group for several days after aSAH. During the 107 day-monitoring period [interquartile range(IQR):92;128], no UCA rupture occurred in either group. UCA volume analysis was performed in 44 patients (60 UCAs): none of the UCAs in the iHTN group and 3 out of 42 (7%) in the control group had a >5 mm3 volume growth (p=0.55). Other morphologic parameters did not exhibit any variations that might indicate an increased risk of rupture in the iHTN group compared to the control group. CONCLUSION: iHTN did not increase the risk of rupture or volume growth of UCAs within several weeks following aSAH. These reassuring results encourage not to refrain, because of the existence of UCAs, from iHTN as an option to prevent cerebral infarction during cerebral vasospasm.

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.

Verification of a simplified aneurysm dimensionless flow parameter to predict intracranial aneurysm rupture status.

OBJECTIVES: Aneurysm number (An) is a novel prediction tool utilizing parameters of pulsatility index (PI) and aneurysm geometry. An has been shown to have the potential to differentiate intracranial aneurysm (IA) rupture status. The objective of this study is to investigate the feasibility and accuracy of An for IA rupture status prediction using Australian based clinical data. METHODS: A retrospective study was conducted across three tertiary referral hospitals between November 2017 and November 2020 and all saccular IAs with known rupture status were included. Two sets of An values were calculated based on two sets of PI values previously reported in the literature. RESULTS: Five hundred and four IA cases were included in this study. The results demonstrated no significant difference between ruptured and unruptured status when using An ≥1 as the discriminator. Further analysis showed no strong correlation between An and IA subtypes. The area under the curve (AUC) indicated poor performance in predicting rupture status (AUC1 = 0.55 and AUC2 = 0.56). CONCLUSIONS: This study does not support An ≥1 as a reliable parameter to predict the rupture status of IAs based on a retrospective cohort. Although the concept of An is supported by hemodynamic aneurysm theory, further research is needed before it can be applied in the clinical setting. ADVANCES IN KNOWLEDGE: This study demonstrates that the novel prediction tool, An, proposed in 2020 is not reliable and that further research of this hemodynamic model is needed before it can be incorporated into the prediction of IA rupture status.

Patient-specific cerebral 3D vessel model reconstruction using deep learning.

Three-dimensional vessel model reconstruction from patient-specific magnetic resonance angiography (MRA) images often requires some manual maneuvers. This study aimed to establish the deep learning (DL)-based method for vessel model reconstruction. Time of flight MRA of 40 patients with internal carotid artery aneurysms was prepared, and three-dimensional vessel models were constructed using the threshold and region-growing method. Using those datasets, supervised deep learning using 2D U-net was performed to reconstruct 3D vessel models. The accuracy of the DL-based vessel segmentations was assessed using 20 MRA images outside the training dataset. The dice coefficient was used as the indicator of the model accuracy, and the blood flow simulation was performed using the DL-based vessel model. The created DL model could successfully reconstruct a three-dimensional model in all 60 cases. The dice coefficient in the test dataset was 0.859. Of note, the DL-generated model proved its efficacy even for large aneurysms (> 10 mm in their diameter). The reconstructed model was feasible in performing blood flow simulation to assist clinical decision-making. Our DL-based method could successfully reconstruct a three-dimensional vessel model with moderate accuracy. Future studies are warranted to exhibit that DL-based technology can promote medical image processing.