Intracranial aneurysm segmentation in 3D CT angiography: Method and quantitative validation with and without prior noise filtering

High-throughput 3DRA segmentation of brain vasculature and aneurysms using deep learning

BACKGROUND AND OBJECTIVES

Automatic segmentation of the cerebral vasculature and aneurysms facilitates incidental detection of aneurysms. The assessment of aneurysm rupture risk assists with pre-operative treatment planning and enables in-silico investigation of cerebral hemodynamics within and in the vicinity of aneurysms. However, ensuring precise and robust segmentation of cerebral vessels and aneurysms in neuroimaging modalities such as three-dimensional rotational angiography (3DRA) is challenging. The vasculature constitutes a small proportion of the image volume, resulting in a large class imbalance (relative to surrounding brain tissue). Additionally, aneurysms and vessels have similar image/appearance characteristics, making it challenging to distinguish the aneurysm sac from the vessel lumen.

METHODS

We propose a novel multi-class convolutional neural network to tackle these challenges and facilitate the automatic segmentation of cerebral vessels and aneurysms in 3DRA images. The proposed model is trained and evaluated on an internal multi-center dataset and an external publicly available challenge dataset.

RESULTS

On the internal clinical dataset, our method consistently outperformed several state-of-the-art approaches for vessel and aneurysm segmentation, achieving an average Dice score of 0.81 (0.15 higher than nnUNet) and an average surface-to-surface error of 0.20 mm (less than the in-plane resolution (0.35 mm/pixel)) for aneurysm segmentation; and an average Dice score of 0.91 and average surface-to-surface error of 0.25 mm for vessel segmentation. In 223 cases of a clinical dataset, our method accurately segmented 190 aneurysm cases.

CONCLUSIONS

The proposed approach can help address class imbalance problems and inter-class interference problems in multi-class segmentation. Besides, this method performs consistently on clinical datasets from four different sources and the generated results are qualified for hemodynamic simulation. Code available at https://github.com/cistib/vessel-aneurysm-segmentation.

Deep learning-based recognition and segmentation of intracranial aneurysms under small sample size

The manual identification and segmentation of intracranial aneurysms (IAs) involved in the 3D reconstruction procedure are labor-intensive and prone to human errors. To meet the demands for routine clinical management and large cohort studies of IAs, fast and accurate patient-specific IA reconstruction becomes a research Frontier. In this study, a deep-learning-based framework for IA identification and segmentation was developed, and the impacts of image pre-processing and convolutional neural network (CNN) architectures on the framework's performance were investigated. Three-dimensional (3D) segmentation-dedicated architectures, including 3D UNet, VNet, and 3D Res-UNet were evaluated. The dataset used in this study included 101 sets of anonymized cranial computed tomography angiography (CTA) images with 140 IA cases. After the labeling and image pre-processing, a training set and test set containing 112 and 28 IA lesions were used to train and evaluate the convolutional neural network mentioned above. The performances of three convolutional neural networks were compared in terms of training performance, segmentation performance, and segmentation efficiency using multiple quantitative metrics. All the convolutional neural networks showed a non-zero voxel-wise recall (V-Recall) at the case level. Among them, 3D UNet exhibited a better overall segmentation performance under the relatively small sample size. The automatic segmentation results based on 3D UNet reached an average V-Recall of 0.797 ± 0.140 (3.5% and 17.3% higher than that of VNet and 3D Res-UNet), as well as an average dice similarity coefficient (DSC) of 0.818 ± 0.100, which was 4.1%, and 11.7% higher than VNet and 3D Res-UNet. Moreover, the average Hausdorff distance (HD) of the 3D UNet was 3.323 ± 3.212 voxels, which was 8.3% and 17.3% lower than that of VNet and 3D Res-UNet. The three-dimensional deviation analysis results also showed that the segmentations of 3D UNet had the smallest deviation with a max distance of +1.4760/-2.3854 mm, an average distance of 0.3480 mm, a standard deviation (STD) of 0.5978 mm, a root mean square (RMS) of 0.7269 mm. In addition, the average segmentation time (AST) of the 3D UNet was 0.053s, equal to that of 3D Res-UNet and 8.62% shorter than VNet. The results from this study suggested that the proposed deep learning framework integrated with 3D UNet can provide fast and accurate IA identification and segmentation.

Toward human intervention-free clinical diagnosis of intracranial aneurysm via deep neural network

Intracranial aneurysm (IA) is an enormous threat to human health, which often results in nontraumatic subarachnoid hemorrhage or dismal prognosis. Diagnosing IAs on commonly used computed tomographic angiography (CTA) examinations remains laborious and time consuming, leading to error-prone results in clinical practice, especially for small targets. In this study, we propose a fully automatic deep-learning model for IA segmentation that can be applied to CTA images. Our model, called Global Localization-based IA Network (GLIA-Net), can incorporate the global localization prior and generates the fine-grain three-dimensional segmentation. GLIA-Net is trained and evaluated on a big internal dataset (1,338 scans from six institutions) and two external datasets. Evaluations show that our model exhibits good tolerance to different settings and achieves superior performance to other models. A clinical experiment further demonstrates the clinical utility of our technique, which helps radiologists in the diagnosis of IAs.

•

GLIA-Net is a deep learning method for the clinical diagnosis of IAs

•

It can be applied directly to CTA images without any laborious preprocessing

•

A clinical study demonstrates its effectiveness in assisting diagnosis

•

An IA dataset of 1,338 CTA cases from six institutions is publicly released

Intracranial aneurysms (IAs) are enormous threats to human health with a prevalence of approximately 4%. The rupture of IAs usually causes death or severe damage to the patients. To enhance the clinical diagnosis of IAs, we present a deep learning model (GLIA-Net) for IA detection and segmentation without laborious human intervention, which achieves superior diagnostic performance validated by quantitative evaluations as well as a sophisticated clinical study. We anticipate that the publicly released data and the artificial intelligence technique would help to transform the clinical diagnostics and precision treatments of cerebrovascular diseases. They may also revolutionize the landscape of healthcare and biomedical research in the future.

Accuracy of bone segmentation and surface generation strategies analyzed by using synthetic CT volumes

Different kinds of bone measurements are commonly derived from computed-tomography (CT) volumes to answer a multitude of questions in biology and related fields. The underlying steps of bone segmentation and, optionally, polygon surface generation are crucial to keep the measurement error small. In this study, the performance of different, easily accessible segmentation techniques (global thresholding, automatic local thresholding, weighted random walk, neural network, and watershed) and surface generation approaches (different algorithms combined with varying degrees of simplification) was analyzed and recommendations for minimizing inaccuracies were derived. The different approaches were applied to synthetic CT volumes for which the correct segmentation and surface geometry were known. The most accurate segmentations of the synthetic volumes were achieved by setting a case-specific window to the gray value histogram and subsequently applying automatic local thresholding with appropriately chosen thresholding method and radius. Surfaces generated by the Amira® module Generate Lego Surface in combination with careful surface simplification were the most accurate. Surfaces with sub-voxel accuracy were obtained even for synthetic CT volumes with low contrast-to-noise ratios. Segmentation trials with real CT volumes supported the findings. Very accurate segmentations and surfaces can be derived from CT volumes by using readily accessible software packages. The presented results and derived recommendations will help to reduce the measurement error in future studies. Furthermore, the demonstrated strategies for assessing segmentation and surface qualities can be adopted to quantify the performance of new segmentation approaches in future studies.

Variant facial artery anatomy revisited: Conventional angiography performed in 284 cases

A number of studies have evaluated the variable courses of facial artery. However, the results of these differed substantially from each other so not consistent relationships have yet been established. There has also yet to be a relevant study using conventional angiography.We assessed the variant branching pattern of the facial artery and its branches using conventional angiography.Two radiologists retrospectively reviewed 284 cases of angiographies of the external carotid artery in 198 patients. The courses of the facial artery and infraorbital branch of the maxillary artery were classified into 4 types and 2 types, according to the end branch.Among 284 cases of facial artery, type 1 (angular branch) made up 104 cases (36.6%), type 2 (lateral nasal branch) made up 138 cases (48.6%), type 3 (superior labial branch) made up 24 cases (8.5%), and type 4 (inferior labial branch) made up 18 cases (6.3%).Regarding the 284 total cases of maxillary artery, 163 cases (57.4%) had anastomosis with the angular artery or extended to the territory of the angular artery. In addition, 121 cases (42.6%) had nothing done in regard to the angular artery.The results may be helpful for avoiding complications related to facial and maxillary arteries during facial surgeries and cosmetic procedures.

Evaluation of 3D printed carotid anatomical models in planning carotid artery stenting

Background

We aimed to investigate the potential role of threedimensional printed anatomical models in pre-procedural planning, practice, and selection of carotid artery stent and embolic protection device size and location.

Methods

A total of 16 patients (10 males, 6 females; mean age 75.6±4.7 years; range, 68 to 81 years) who underwent carotid artery stenting with an embolic protection device between January 2017 and February 2019 were retrospectively analyzed. The sizing was based on intraprocedural angiography findings with the same brand stent using distal protection device. Pre-procedural computed tomography angiography images used for diagnosis were obtained and modeled with three-dimensional printing method. Pre-procedural and threedimensional data regarding the size of stents and protection devices and implantation sites were compared.

Results

Measurements obtained from three-dimensional models manually and segmentation images from software were found to be similar and both were smaller than actually used for stent and embolic protection device sizes. The rates of carotid artery stenosis were similar with manual and software methods, but were lower than the quantitative angiographic measurements. Device implantation sites detected by the manual and software methods were different than the actual setting.

Conclusion

The planning and practicing of procedure with threedimensional models may reduce the operator-dependent variables, shorten the operation time, decrease X-ray exposure, and increase the procedural success.

A new hypothesis on the role of vessel topology in cerebral aneurysm initiation

Aneurysm pathogenesis is thought to be strongly linked with hemodynamical effects. According to our current knowledge, the formation process is initiated by locally disturbed flow conditions. The aim of the current work is to provide a numerical investigation on the role of the flow field at the stage of the initiation, before the aneurysm formation. Digitally reconstructed pre-aneurysmal geometries are used to examine correlations of the flow patterns to the location and direction of the aneurysms formed later. We argue that a very specific rotational flow pattern is present in all the investigated cases marking the location of the later aneurysm and that these flow patterns provide the mechanical load on the wall that can lead to a destructive remodelling in the vessel wall. Furthermore, these patterns induce elevated vessel surface related variables (e.g. wall shear stress (WSS), wall shear stress gradient (WSSG) and oscillatory shear index (OSI)), in agreement with the previous findings. We emphasise that the analysis of the flow patterns provides a deeper insight and a more robust numerical methodology compared to the sole examination of the aforementioned surface quantities.

A new cerebral vessel benchmark dataset (CAPUT) for validation of image-based aneurysm deformation estimation algorithms

Hemodynamic properties and deformation of vessel structures are assumed to be correlated to the initiation, development, and rupture of cerebral aneurysms. Therefore, precise quantification of wall motion is essential. However, using standard-of-care imaging data, approaches for patient-specific estimation of pulsatile deformation are prone to uncertainties due to, e.g., contrast agent inflow-related intensity changes and small deformation compared to the image resolution. A ground truth dataset that allows evaluating and finetuning algorithms for deformation estimation is lacking. We designed a flow phantom with deformable structures that resemble cerebral vessels and exhibit physiologically plausible deformation. The deformation was simultaneously recorded using a flat panel CT and a video camera, yielding video data with higher resolution and SNR, which was used to compute 'ground truth' structure deformation measures. The dataset was further applied to evaluate registration-based deformation estimation. The results illustrate that registration approaches can be used to estimate deformation with adequate precision. Yet, the accuracy depended on the registration parameters, illustrating the need to evaluate and finetune deformation estimation approaches by ground truth data. To fill the existing gap, the acquired benchmark dataset is provided freely available as the CAPUT (Cerebral Aneurysm PUlsation Testing) dataset, accessible at https://www.github.com/IPMI-ICNS-UKE/CAPUT .

Real-World Variability in the Prediction of Intracranial Aneurysm Wall Shear Stress: The 2015 International Aneurysm CFD Challenge

Purpose

Image-based computational fluid dynamics (CFD) is widely used to predict intracranial aneurysm wall shear stress (WSS), particularly with the goal of improving rupture risk assessment. Nevertheless, concern has been expressed over the variability of predicted WSS and inconsistent associations with rupture. Previous challenges, and studies from individual groups, have focused on individual aspects of the image-based CFD pipeline. The aim of this Challenge was to quantify the total variability of the whole pipeline.

Methods

3D rotational angiography image volumes of five middle cerebral artery aneurysms were provided to participants, who were free to choose their segmentation methods, boundary conditions, and CFD solver and settings. Participants were asked to fill out a questionnaire about their solution strategies and experience with aneurysm CFD, and provide surface distributions of WSS magnitude, from which we objectively derived a variety of hemodynamic parameters.

Results

A total of 28 datasets were submitted, from 26 teams with varying levels of self-assessed experience. Wide variability of segmentations, CFD model extents, and inflow rates resulted in interquartile ranges of sac average WSS up to 56%, which reduced to < 30% after normalizing by parent artery WSS. Sac-maximum WSS and low shear area were more variable, while rank-ordering of cases by low or high shear showed only modest consensus among teams. Experience was not a significant predictor of variability.

Conclusions

Wide variability exists in the prediction of intracranial aneurysm WSS. While segmentation and CFD solver techniques may be difficult to standardize across groups, our findings suggest that some of the variability in image-based CFD could be reduced by establishing guidelines for model extents, inflow rates, and blood properties, and by encouraging the reporting of normalized hemodynamic parameters.

A priori knowledge integration for the detection of cerebral aneurysm

The detection of intracranial aneurysms is of a paramount effect in the prevention of cerebral subarachnoid hemorrhage. We propose in this paper, a new approach to detect cerebral aneurysm in digital subtraction angiography (DSA) images by fusing several sources of knowledge. After a brief description of a priori knowledge that the expert has provided about cerebral aneurysm, we propose a system architecture including fuzzy modeling and data fusion. The results on the studied cases are very promising.

Analysis of the influence of imaging-related uncertainties on cerebral aneurysm deformation quantification using a no-deformation physical flow phantom

Cardiac-cycle related pulsatile aneurysm motion and deformation is assumed to provide valuable information for assessing cerebral aneurysm rupture risk. Accordingly, numerous studies addressed quantification of cerebral aneurysm wall motion and deformation. Most of them utilized in vivo imaging data, but image-based aneurysm deformation quantification is subject to pronounced uncertainties: unknown ground-truth deformation; image resolution in the order of the expected deformation; direct interplay between contrast agent inflow and image intensity. To analyze the impact of the uncertainties on deformation quantification, a multi-imaging modality ground-truth phantom study is performed. A physical flow phantom was designed that allowed simulating pulsatile flow through a variety of modeled cerebral vascular structures. The phantom was imaged using different modalities [MRI, CT, 3D-RA] and mimicking physiologically realistic flow conditions. Resulting image data was analyzed by an established registration-based approach for automated wall motion quantification. The data reveals severe dependency between contrast media inflow-related image intensity changes and the extent of estimated wall deformation. The study illustrates that imaging-related uncertainties affect the accuracy of cerebral aneurysm deformation quantification, suggesting that in vivo imaging studies have to be accompanied by ground-truth phantom experiments to foster data interpretation and to prove plausibility of the applied image analysis algorithms.

A practical guide to cardiovascular 3D printing in clinical practice: Overview and examples

The advent of more advanced 3D image processing, reconstruction, and a variety of three-dimensional (3D) printing technologies using different materials has made rapid and fairly affordable anatomically accurate models much more achievable. These models show great promise in facilitating procedural and surgical planning for complex congenital and structural heart disease. Refinements in 3D printing technology lend itself to advanced applications in the fields of bio-printing, hemodynamic modeling, and implantable devices. As a novel technology with a large variability in software, processing tools and printing techniques, there is not a standardized method by which a clinician can go from an imaging data-set to a complete model. Furthermore, anatomy of interest and how the model is used can determine the most appropriate technology. In this over-view we discuss, from the standpoint of a clinical professional, image acquisition, processing, and segmentation by which a printable file is created. We then review the various printing technologies, advantages and disadvantages when printing the completed model file, and describe clinical scenarios where 3D printing can be utilized to address therapeutic challenges.

Virtual endovascular treatment of intracranial aneurysms: models and uncertainty

Virtual endovascular treatment models (VETMs) have been developed with the view to aid interventional neuroradiologists and neurosurgeons to pre-operatively analyze the comparative efficacy and safety of endovascular treatments for intracranial aneurysms. Based on the current state of VETMs in aneurysm rupture risk stratification and in patient-specific prediction of treatment outcomes, we argue there is a need to go beyond personalized biomechanical flow modeling assuming deterministic parameters and error-free measurements. The mechanobiological effects associated with blood clot formation are important factors in therapeutic decision making and models of post-treatment intra-aneurysmal biology and biochemistry should be linked to the purely hemodynamic models to improve the predictive power of current VETMs. The influence of model and parameter uncertainties associated to each component of a VETM is, where feasible, quantified via a random-effects meta-analysis of the literature. This allows estimating the pooled effect size of these uncertainties on aneurysmal wall shear stress. From such meta-analyses, two main sources of uncertainty emerge where research efforts have so far been limited: (1) vascular wall distensibility, and (2) intra/intersubject systemic flow variations. In the future, we suggest that current deterministic computational simulations need to be extended with strategies for uncertainty mitigation, uncertainty exploration, and sensitivity reduction techniques. WIREs Syst Biol Med 2017, 9:e1385. doi: 10.1002/wsbm.1385 For further resources related to this article, please visit the WIREs website.

Does the DSA reconstruction kernel affect hemodynamic predictions in intracranial aneurysms? An analysis of geometry and blood flow variations

BACKGROUND

Computational fluid dynamics (CFD) blood flow predictions in intracranial aneurysms promise great potential to reveal patient-specific flow structures. Since the workflow from image acquisition to the final result includes various processing steps, quantifications of the individual introduced potential error sources are required.

METHODS

Three-dimensional (3D) reconstruction of the acquired imaging data as input to 3D model generation was evaluated. Six different reconstruction modes for 3D digital subtraction angiography (DSA) acquisitions were applied to eight patient-specific aneurysms. Segmentations were extracted to compare the 3D luminal surfaces. Time-dependent CFD simulations were carried out in all 48 configurations to assess the velocity and wall shear stress (WSS) variability due to the choice of reconstruction kernel.

RESULTS

All kernels yielded good segmentation agreement in the parent artery; deviations of the luminal surface were present at the aneurysm neck (up to 34.18%) and in distal or perforating arteries. Observations included pseudostenoses as well as noisy surfaces, depending on the selected reconstruction kernel. Consequently, the hemodynamic predictions show a mean SD of 11.09% for the aneurysm neck inflow rate, 5.07% for the centerline-based velocity magnitude, and 17.83%/9.53% for the mean/max aneurysmal WSS, respectively. In particular, vessel sections distal to the aneurysms yielded stronger variations of the CFD values.

CONCLUSIONS

The choice of reconstruction kernel for DSA data influences the segmentation result, especially for small arteries. Therefore, if precise morphology measurements or blood flow descriptions are desired, a specific reconstruction setting is required. Furthermore, research groups should be encouraged to denominate the kernel types used in future hemodynamic studies.

Digital subtraction CT angiography for the detection of posterior inferior cerebellar artery aneurysms: comparison with digital subtraction angiography

OBJECTIVE

To evaluate the diagnostic accuracy of digital subtraction CT angiography (DS-CTA) in detecting posterior inferior cerebellar artery (PICA) aneurysms with digital subtraction angiography (DSA) as reference standard.

METHODS

A total of 115 patients, including 56 patients diagnosed with PICA aneurysms by CTA or DSA and 59 non-PICA-aneurysm patients were included in this retrospective study. All patients underwent DS-CTA and DSA. The site of PICA aneurysms and the pattern of haemorrhage were analysed. Sensitivity and specificity of DS-CTA without and with combining haemorrhage pattern in diagnosing PICA aneurysms were evaluated on a per patient and per aneurysm basis with DSA.

RESULTS

Of 115 patients, 56 patients (48.7%) had 61 PICA aneurysms (size range, 1.1-13.5 mm; mean size, 4.9 ± 2.8 mm) on DSA. The sensitivity and specificity in depicting PICA aneurysms were 89.3% and 96.6% on a per patient basis and 90.2% and 93.4% on a per aneurysm basis, while the corresponding values were 94.6% and 96.6% on a per patient basis and 95.1% and 93.4% on a per aneurysm basis when combining with haemorrhage site.

CONCLUSION

DS-CTA has a high sensitivity and specificity in detecting PICA aneurysms compared with DSA. It may be helpful for clinical diagnosis of PICA aneurysms to combine with haemorrhage sites.

KEY POINTS

• CT angiography has a good diagnostic performance in detecting PICA aneurysms. • The haemorrhage location is helpful to detect PICA aneurysms. • Digital subtraction CTA is a preferable diagnostic means for PICA aneurysms.

Cardiac 3D Printing and its Future Directions

Three-dimensional (3D) printing is at the crossroads of printer and materials engineering, noninvasive diagnostic imaging, computer-aided design, and structural heart intervention. Cardiovascular applications of this technology development include the use of patient-specific 3D models for medical teaching, exploration of valve and vessel function, surgical and catheter-based procedural planning, and early work in designing and refining the latest innovations in percutaneous structural devices. In this review, we discuss the methods and materials being used for 3D printing today. We discuss the basic principles of clinical image segmentation, including coregistration of multiple imaging datasets to create an anatomic model of interest. With applications in congenital heart disease, coronary artery disease, and surgical and catheter-based structural disease, 3D printing is a new tool that is challenging how we image, plan, and carry out cardiovascular interventions.

Simulation of MR angiography imaging for validation of cerebral arteries segmentation algorithms

BACKGROUND AND OBJECTIVE

Accurate vessel segmentation of magnetic resonance angiography (MRA) images is essential for computer-aided diagnosis of cerebrovascular diseases such as stenosis or aneurysm. The ability of a segmentation algorithm to correctly reproduce the geometry of the arterial system should be expressed quantitatively and observer-independently to ensure objectivism of the evaluation.

METHODS

This paper introduces a methodology for validating vessel segmentation algorithms using a custom-designed MRA simulation framework. For this purpose, a realistic reference model of an intracranial arterial tree was developed based on a real Time-of-Flight (TOF) MRA data set. With this specific geometry blood flow was simulated and a series of TOF images was synthesized using various acquisition protocol parameters and signal-to-noise ratios. The synthesized arterial tree was then reconstructed using a level-set segmentation algorithm available in the Vascular Modeling Toolkit (VMTK). Moreover, to present versatile application of the proposed methodology, validation was also performed for two alternative techniques: a multi-scale vessel enhancement filter and the Chan-Vese variant of the level-set-based approach, as implemented in the Insight Segmentation and Registration Toolkit (ITK). The segmentation results were compared against the reference model.

RESULTS

The accuracy in determining the vessels centerline courses was very high for each tested segmentation algorithm (mean error rate = 5.6% if using VMTK). However, the estimated radii exhibited deviations from ground truth values with mean error rates ranging from 7% up to 79%, depending on the vessel size, image acquisition and segmentation method.

CONCLUSIONS

We demonstrated the practical application of the designed MRA simulator as a reliable tool for quantitative validation of MRA image processing algorithms that provides objective, reproducible results and is observer independent.

Development of image segmentation methods for intracranial aneurysms

Though providing vital means for the visualization, diagnosis, and quantification of decision-making processes for the treatment of vascular pathologies, vascular segmentation remains a process that continues to be marred by numerous challenges. In this study, we validate eight aneurysms via the use of two existing segmentation methods; the Region Growing Threshold and Chan-Vese model. These methods were evaluated by comparison of the results obtained with a manual segmentation performed. Based upon this validation study, we propose a new Threshold-Based Level Set (TLS) method in order to overcome the existing problems. With divergent methods of segmentation, we discovered that the volumes of the aneurysm models reached a maximum difference of 24%. The local artery anatomical shapes of the aneurysms were likewise found to significantly influence the results of these simulations. In contrast, however, the volume differences calculated via use of the TLS method remained at a relatively low figure, at only around 5%, thereby revealing the existence of inherent limitations in the application of cerebrovascular segmentation. The proposed TLS method holds the potential for utilisation in automatic aneurysm segmentation without the setting of a seed point or intensity threshold. This technique will further enable the segmentation of anatomically complex cerebrovascular shapes, thereby allowing for more accurate and efficient simulations of medical imagery.

Segmentation of intracranial vessels and aneurysms in phase contrast magnetic resonance angiography using multirange filters and local variances

Segmentation of intensity varying and low-contrast structures is an extremely challenging and rewarding task. In computer-aided diagnosis of intracranial aneurysms, segmenting the high-intensity major vessels along with the attached low-contrast aneurysms is essential to the recognition of this lethal vascular disease. It is particularly helpful in performing early and noninvasive diagnosis of intracranial aneurysms using phase contrast magnetic resonance angiographic (PC-MRA) images. The major challenges of developing a PC-MRA-based segmentation method are the significantly varying voxel intensity inside vessels with different flow velocities and the signal loss in the aneurysmal regions where turbulent flows occur. This paper proposes a novel intensity-based algorithm to segment intracranial vessels and the attached aneurysms. The proposed method can handle intensity varying vasculatures and also the low-contrast aneurysmal regions affected by turbulent flows. It is grounded on the use of multirange filters and local variances to extract intensity-based image features for identifying contrast varying vasculatures. The extremely low-intensity region affected by turbulent flows is detected according to the topology of the structure detected by multirange filters and local variances. The proposed method is evaluated using a phantom image volume with an aneurysm and four clinical cases. It achieves 0.80 dice score in the phantom case. In addition, different components of the proposed method-the multirange filters, local variances, and topology-based detection-are evaluated in the comparison between the proposed method and its lower complexity variants. Owing to the analogy between these variants and existing vascular segmentation methods, this comparison also exemplifies the advantage of the proposed method over the existing approaches. It analyzes the weaknesses of these existing approaches and justifies the use of every component involved in the proposed method. It is shown that the proposed method is capable of segmenting blood vessels and the attached aneurysms on PC-MRA images.

Quantification of intracranial aneurysm morphodynamics from ECG-gated CT angiography

RATIONALE AND OBJECTIVES

Aneurysm morphodynamics is potentially relevant for assessing aneurysm rupture risk. A method is proposed for automated quantification and visualization of intracranial aneurysm morphodynamics from electrocardiogram (ECG)-gated computed tomography angiography (CTA) data.

MATERIALS AND METHODS

A prospective study was performed in 19 aneurysms from 14 patients with diagnostic workup for recently discovered aneurysms (n = 15) or follow-up of untreated known aneurysms (n = 4). The study was approved by the Institutional Review Board of the hospital and written informed consent was obtained from each patient. An image postprocessing method was developed for quantifying aneurysm volume changes and visualizing local displacement of the aneurysmal wall over a heart cycle using multiphase ECG-gated (four-dimensional) CTA. Percentage volume changes over the heart cycle were determined for aneurysms, surrounding arteries, and the skull.

RESULTS

Pulsation of the aneurysm and its surrounding vasculature during the heart cycle could be assessed from ECG-gated CTA data. The percentage aneurysmal volume change ranged from 3% to 18%.

CONCLUSION

ECG-gated CTA can be used to study morphodynamics of intracranial aneurysms. The proposed image analysis method is capable of quantifying the volume changes and visualizing local displacement of the vascular structures over the cardiac cycle.

Digital subtraction CT angiography for detection of intracranial aneurysms: comparison with three-dimensional digital subtraction angiography

PURPOSE

To evaluate the diagnostic accuracy of digital subtraction computed tomographic (CT) angiography in the detection of intracranial aneurysms compared with three-dimensional (3D) rotational digital subtraction angiography (DSA), as reference standard, in a large cohort in a single center.

MATERIALS AND METHODS

The study was waived by the institutional review board because of its retrospective nature. A total of 513 patients clinically suspected of having or with known intracranial aneurysms and other cerebral vascular diseases underwent both digital subtraction CT angiography with a dual-source CT scanner and 3D DSA, with a median interval of 1 day; 436 patients (84.9%) had acute subarachnoid hemorrhage at presentation. The sensitivity, specificity, and accuracy of digital subtraction CT angiography in depicting aneurysm were analyzed on a per-patient and per-aneurysm basis, with 3D DSA as the reference standard. The sensitivity, specificity, and accuracy of digital subtraction CT angiography in depicting aneurysms of different diameter (ie, <3 mm, 3-5 mm, 5-10 mm, and >10 mm) and of aneurysms at different locations in the anterior and posterior circulation were calculated. Kappa statistics were calculated to quantify inter- and intrareader variability in detecting aneurysms by using digital subtraction CT angiography for 100 patients.

RESULTS

Of 513 patients, 106 (20.7%) had no aneurysms, while 407 patients (79.3%) had 459 aneurysms at 3D DSA. Digital subtraction CT angiography correctly depicted 456 (99.3%) of the 459 aneurysms. By using 3D DSA as the standard of reference, the sensitivity and specificity of depicting intracranial aneurysms were 97.8% (398 of 407) and 88.7% (94 of 106), respectively, on a per-patient basis, and 96.5% (443 of 459) and 87.8% (94 of 107), respectively, on a per-aneurysm basis. Digital subtraction CT angiography had sensitivities of 91.3% (42 of 46), 94.0% (140 of 149), 98.4% (186 of 189), and 100% (75 of 75) in depicting aneurysms of less than 3 mm, between 3 mm but less than 5 mm, between 5 mm but less than 10 mm, and 10 mm or greater, respectively, and of 95.8% (276 of 288) and 97.7% (167 of 171) in depicting anterior circulation and posterior circulation aneurysms, respectively. Excellent inter- and intrareader agreement was found on a per-patient (κ=0.900 and 0.939, both P<.001) and per-aneurysm basis (κ=0.846 and 0.921, both P<.001) for the detection of intracranial aneurysms with digital subtraction CT angiography.

CONCLUSION

Digital subtraction CT angiography has a high sensitivity and specificity in depicting intracranial aneurysms with different sizes and at different locations, compared with 3D DSA.