Imaging of cerebral aneurysms: a clinical perspective

Reducing frame rate and pulse rate for routine diagnostic cerebral angiography: ALARA principles in practice

OBJECTIVE

Diagnostic cerebral angiograms (DCAs) are widely used in neurosurgery due to their high sensitivity and specificity to diagnose and characterize pathology using ionizing radiation. Eliminating unnecessary radiation is critical to reduce risk to patients, providers, and health care staff. We investigated if reducing pulse and frame rates during routine DCAs would decrease radiation burden without compromising image quality.

METHODS

We performed a retrospective review of prospectively acquired data after implementing a quality improvement protocol in which pulse rate and frame rate were reduced from 15 p/s to 7.5 p/s and 7.5 f/s to 4.0 f/s respectively. Radiation doses and exposures were calculated. Two endovascular neurosurgeons reviewed randomly selected angiograms of both doses and blindly assessed their quality.

RESULTS

A total of 40 consecutive angiograms were retrospectively analyzed, 20 prior to the protocol change and 20 after. After the intervention, radiation dose, radiation per run, total exposure, and exposure per run were all significantly decreased even after adjustment for BMI (all p<0.05). On multivariable analysis, we identified a 46% decrease in total radiation dose and 39% decrease in exposure without compromising image quality or procedure time.

CONCLUSIONS

We demonstrated that for routine DCAs, pulse rate of 7.5 with a frame rate of 4.0 is sufficient to obtain diagnostic information without compromising image quality or elongating procedure time. In the interest of patient, provider, and health care staff safety, we strongly encourage all interventionalists to be cognizant of radiation usage to avoid unnecessary radiation exposure and consequential health risks.

Detection of cerebral aneurysm and intracranial vertebral dissection using non-enhanced magnetic resonance imaging in emergency setting: Emphasis on magnitude image of susceptibility-weighted image

PURPOSE

To evaluate image features and diagnostic performance of susceptibility-weighted image (SWI) in detection of intracranial vertebral artery dissection (VAD) and unruptured intracranial aneurysm (UIA).

MATERIALS AND METHODS

From January 2015 to December 2021, symptomatic patients who underwent 3.0 T MR SWI were recruited. For study group, transfemoral cerebral angiography-proven lesions were included, while 1:1 matched control group with MR angiography were included. Image features of SWI were evaluated. Diagnostic performance and interobserver agreements were calculated for detecting VAD with stenosis and UIA greater than 7 mm.

RESULTS

Total of 110 patients (mean age: 60.92 years, female: 60/110) were included. In the study group (N = 55), 21 patients (38.2%) had VAD, while 34 patients (61.8%) had UIA. For SWI-detectable VAD, larger parent artery (PA)-dilatation ratio was observed (1.36 vs. 1.84, p = 0.034). For SWI-detectable UIA, larger PA-dome ratio (1.32 vs. 1.90, p = 0.020) and larger PA-height ratio (1.25 vs. 1.77, p = 0.005) were observed. The diagnostic performance and kappa values for VAD with stenosis were as follow: sensitivity: 91.7 (95% CI: 61.5-99.8); specificity: 93.9 (95% CI: 87.2-97.7); к: 0.80. The diagnostic performance for UIA larger than 7 mm were as follow: sensitivity: 87.5 (95% CI: 47.4-99.7); specificity: 95.1 (95% CI: 88.9-98.4); к: 0.73.

CONCLUSION

SWI-detectable lesions were VAD with larger PA-dilatation ratio, and UIA with larger PA-dome ratio, and PA-height ratio. SWI was able to accurately detect VAD with stenosis and UIA larger than 7 mm with substantial interobserver agreements.

Comparison of 1.5 T and 3 T magnetic resonance angiography for detecting cerebral aneurysms using deep learning-based computer-assisted detection software

PURPOSE

To compare the diagnostic performance of 1.5 T versus 3 T magnetic resonance angiography (MRA) for detecting cerebral aneurysms with clinically available deep learning-based computer-assisted detection software (EIRL aneurysm® [EIRL_an]), which has been approved by the Japanese Pharmaceuticals and Medical Devices Agency. We also sought to analyze the causes of potential false positives.

METHODS

In this single-center, retrospective study, we evaluated the MRA scans of 90 patients who underwent head MRA (1.5 T and 3 T in 45 patients each) in clinical practice. Overall, 51 patients had 70 aneurysms. We used MRI from a vendor not included in the dataset used to create the EIRL_an algorithm. Two radiologists determined the ground truth, the accuracy of the candidates noted by EIRL_an, and the causes of false positives. The sensitivity, number of false positives per case (FPs/case), and the causes of false positives were compared between 1.5 T and 3 T MRA. Pearson's χ2 test, Fisher's exact test, and the Mann‒Whitney U test were used for the statistical analyses as appropriate.

RESULTS

The sensitivity was high for 1.5 T and 3 T MRA (0.875‒1), but the number of FPs/case was significantly higher with 3 T MRA (1.511 vs. 2.578, p < 0.001). The most common causes of false positives (descending order) were the origin/bifurcation of vessels/branches, flow-related artifacts, and atherosclerosis and were similar between 1.5 T and 3 T MRA.

CONCLUSION

EIRL_an detected significantly more false-positive lesions with 3 T than with 1.5 T MRA in this external validation study. Our data may help physicians with limited experience with MRA to correctly diagnose aneurysms using EIRL_an.

Systematic review of adherence to the standards for reporting of diagnostic accuracy studies (STARD) 2015 reporting guideline in cerebral aneurysm imaging diagnostic accuracy studies

BACKGROUND

Diagnostic neuroimaging plays an essential role in guiding clinical decision-making in the management of patients with cerebral aneurysms. Imaging technologies for investigating cerebral aneurysms constantly evolve, and clinicians rely on the published literature to remain up to date. Reporting guidelines have been developed to standardise and strengthen the reporting of clinical evidence. Therefore, it is essential that radiological diagnostic accuracy studies adhere to such guidelines to ensure completeness of reporting. Incomplete reporting hampers the reader's ability to detect bias, determine generalisability of study results or replicate investigation parameters, detracting from the credibility and reliability of studies.

OBJECTIVE

The purpose of this systematic review was to evaluate adherence to the Standards for Reporting of Diagnostic Accuracy Studies (STARD) 2015 reporting guideline amongst imaging diagnostic accuracy studies for cerebral aneurysms.

METHODS

A systematic search for cerebral aneurysm imaging diagnostic accuracy studies was conducted. Journals were cross examined against the STARD 2015 checklist and their compliance with item numbers was recorded.

RESULTS

The search yielded 66 articles. The mean number of STARD items reported was 24.2 ± 2.7 (71.2% ± 7.9%), with a range of 19 to 30 out of a maximum number of 34 items.

CONCLUSION

Taken together, these results indicate that adherence to the STARD 2015 guideline in cerebral aneurysm imaging diagnostic accuracy studies was moderate. Measures to improve compliance include mandating STARD 2015 adherence in instructions to authors issued by journals.

FSTIF-UNet: A Deep Learning-Based Method Towards Automatic Segmentation of Intracranial Aneurysms in Un-Reconstructed 3D-RA

Segmentation of intracranial aneurysms (IAs) is an important step for the diagnosis and treatment of IAs. However, the process by which clinicians manually recognize and localize IAs is overly labor intensive. This study aims to develop a deep-learning-based framework (defined as FSTIF-UNet) towards IAs segmentation in un-reconstructed 3D Rotational Angiography (3D-RA) images. 3D-RA sequences from 300 patients with IAs from Beijing Tiantan Hospital are enrolled. Inspired by radiologists' clincial skills, a Skip-Review attention mechanism is proposed to repeatedly fuse the long-term spatiotemporal features of several images with the most obvious IA's features (sellected by a pre-detection network). Then, a Conv-LSTM is used to fuse the short-term spatiotemporal features of the selected 15 3D-RA images from the equally-spaced viewing angles. The combination of the two modules realizes the full-scale spatiotemporal information fusion of the 3D-RA sequence. FSTIF-UNet achieves DSC, IoU, Sens, Haus, and F1-Score of 0.9109, 0.8586, 0.9314, 1.358 and 0.8883, respectively, and time taken for network segmentation is 0.89 s/case. The results show significant improvement in IA segmentation performance with FSTIF-UNet compared with baseline networks (with DSC from 0.8486 - 0.8794). The proposed FSTIF-UNet establishes a practical method to assist the radiologists in clinical diagnosis.

Interobserver reliability of computed tomography angiography in the assessment of ruptured intracranial aneurysm and impact on patient management

BACKGROUND

Aneurysmal subarachnoid hemorrhage is an emergency that can lead to a high mortality rate and many severe complications. It is critical to make a rapid radiological evaluation of ruptured intracranial aneurysms (RIAs) to determine the appropriate surgical treatment.

AIM

To assess the reliability of computed tomography angiography (CTA) in assessing different features of ruptured intracranial aneurysm and its impact on patient management.

METHODS

The final cohort of this study consisted of 146 patients with RIAs (75 male and 71 female) who underwent cerebral CTA. Their age ranged from 25 to 80, and the mean age ± SD was 57 ± 8.95 years. Two readers were asked to assess different features related to the aneurysm and perianeurysmal environment. Inter-observer agreement was measured using kappa statistics. Imaging data extracted from non-contrast computed tomography and CTA were considered to categorize the study population into two groups according to the recommended therapeutic approach.

RESULTS

The inter-observer agreement of both reviewers was excellent for the detection of aneurysms (K = 0.95, P = 0.001), aneurysm location (K = 0.98, P = 0.001), and (K = 0.98, P = 0.001), morphology (K = 0.92, P = 0.001) and margins (K = 0.95, P = 0.001). There was an excellent interobserver agreement for the measurement of aneurysm size (K = 0.89, P = 0.001), neck (K = 0.85, P = 0.001), and dome-to-neck ratio (K = 0.98, P = 0.001). There was an excellent inter-observer agreement for the detection of other aneurysm-related features such as thrombosis (K = 0.82, P = 0.001), calcification (K = 1.0, P = 0.001), bony landmark (K = 0.89, P = 0.001) and branch incorporation (K = 0.91, P = 0.001) as well as perianeurysmal findings including vasospasm (K = 0.91, P = 0.001), perianeurysmal cyst (K = 1.0, P = 0.001) and associated vascular lesions (K = 0.83, P = 0.001). Based on imaging features, 87 patients were recommended to have endovascular treatment, while surgery was recommended in 59 patients. 71.2% of the study population underwent the recommended therapy.

CONCLUSION

CTA is a reproducible promising diagnostic imaging modality for detecting and characterizing cerebral aneurysms.

Detection of cerebral aneurysms using artificial intelligence: a systematic review and meta-analysis

BACKGROUND

Subarachnoid hemorrhage from cerebral aneurysm rupture is a major cause of morbidity and mortality. Early aneurysm identification, aided by automated systems, may improve patient outcomes. Therefore, a systematic review and meta-analysis of the diagnostic accuracy of artificial intelligence (AI) algorithms in detecting cerebral aneurysms using CT, MRI or DSA was performed.

METHODS

MEDLINE, Embase, Cochrane Library and Web of Science were searched until August 2021. Eligibility criteria included studies using fully automated algorithms to detect cerebral aneurysms using MRI, CT or DSA. Following Preferred Reporting Items for Systematic Reviews and Meta-Analysis: Diagnostic Test Accuracy (PRISMA-DTA), articles were assessed using Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Meta-analysis included a bivariate random-effect model to determine pooled sensitivity, specificity, and area under the receiver operator characteristic curve (ROC-AUC).

PROSPERO

CRD42021278454.

RESULTS

43 studies were included, and 41/43 (95%) were retrospective. 34/43 (79%) used AI as a standalone tool, while 9/43 (21%) used AI assisting a reader. 23/43 (53%) used deep learning. Most studies had high bias risk and applicability concerns, limiting conclusions. Six studies in the standalone AI meta-analysis gave (pooled) 91.2% (95% CI 82.2% to 95.8%) sensitivity; 16.5% (95% CI 9.4% to 27.1%) false-positive rate (1-specificity); 0.936 ROC-AUC. Five reader-assistive AI studies gave (pooled) 90.3% (95% CI 88.0% - 92.2%) sensitivity; 7.9% (95% CI 3.5% to 16.8%) false-positive rate; 0.910 ROC-AUC.

CONCLUSION

AI has the potential to support clinicians in detecting cerebral aneurysms. Interpretation is limited due to high risk of bias and poor generalizability. Multicenter, prospective studies are required to assess AI in clinical practice.

Delayed cerebral pseudoaneurysm following surgical and combined-modality therapy for glioblastoma multiforme: illustrative case

BACKGROUND

Post–radiation therapy and chemotherapy cerebral pseudoaneurysms are rare entities. Within previous tumor treatment areas on nonvascular imaging, they are potentially confused as recurrent tumor.

OBSERVATIONS

A 61-year-old man was a long-term survivor of glioblastoma multiforme whose treatment consisted of open biopsy followed by radiotherapy to 60 Gy and systemic carmustine. On surveillance imaging, enlargement of a posttreatment cyst and new enhancing lateral “mural nodule” was first noticed approximately 16 years after initial treatment. Over 12 months, both continued to enlarge. Initially referred to as recurrence, subsequent angiography showed the mural nodule to be an unruptured distal middle cerebral artery pseudoaneurysm within the previous tumor bed. The patient underwent repeat craniotomy for clipping of the aneurysm and biopsy of the cyst wall, which was negative for malignancy.

LESSONS

Delayed pseudoaneurysms following radiation therapy and chemotherapy for malignant brain tumors are rare but have been previously reported. Their appearance on cross-sectional imaging can mimic recurrence, and they should be kept in the differential of new, circumscribed enhancement within such treatment areas.

Thin Slice Unenhanced Brain CT Can Detect Aneurysms Larger than 7 mm

Purpose:

To evaluate the detection rate of intracranial aneurysms on reconstructed thin slice non enhanced CT (NECT) scans.

Methods:

NECT scans from 34 patients with 35 aneurysms and 35 individuals without aneurysms were collected. Thin slice maximum intensity projections of the NECT scans were reconstructed. One observer evaluated the native images twice with a time interval of six month between both passes with respect to the prevalence and location of an aneurysm. The size and location of the aneurysms were evaluated in corresponding CT-Angiography and Time of flight datasets. A logit regression analysis was performed with size and location as dependent variables. 2 × 2 tables were constructed. The sensitivity and false negative rate were calculated for aneurysms with 0–6.9 mm, 7–9.9 mm and 10–20 mm and the under the curve (AUC) was calculated.

Results:

The overall detection rate of the aneurysms was 63% for the first pass and 66% for the second pass in the reconstructed NECT scans. The detection rate of aneurysms is size dependent. The sensitivity to detect aneurysms with a size of 0–6.9 mm was 0.09 and 0.03, for aneurysms with a size of 7–9.9. mm was 0.8 and 0.7 and for aneurysms with a size of 10–20 mm was 0.92 for both passes.

The AUC was 0.77 for the first pass and 0.78 for the second pass.

Conclusions:

NECT scans can be used to detect a significant proportion of intracranial aneurysms larger than 7 mm if properly displayed and reconstructed. These patients should receive further vascular imaging to prevent future aneurysm related subarachnoid hemorrhage.

Detection of clustered anomalies in single-voxel morphometry as a rapid automated method for identifying intracranial aneurysms

Unruptured intracranial aneurysms (UIAs) are prevalent neurovascular anomalies which, in rare circumstances, rupture to cause a catastrophic subarachnoid haemorrhage. Although surgical management can reduce rupture risk, the majority of UIAs exist undiscovered until rupture. Current clinical practice in the detection of UIAs relies heavily on manual radiological review of standard imaging modalities. Recent computer-aided UIA diagnoses can sensitively detect and measure UIAs within cranial angiograms but remain limited to low specificities whose output also requires considerable radiologist interpretation not amenable to broad screening efforts. To address these limitations, we have developed a novel automatic pipeline algorithm which inputs medical images and outputs detected UIAs by characterising single-voxel morphometry of segmented neurovasculature. Once neurovascular anatomy of a specified resolution is segmented, correlations between voxel-specific morphometries are estimated and spatially-clustered outliers are identified as UIA candidates. Our automated solution detects UIAs within magnetic resonance angiograms (MRA) at unmatched 86% specificity and 81% sensitivity using 3 min on a conventional laptop. Our approach does not rely on interpatient comparisons or training datasets which could be difficult to amass and process for rare incidentally discovered UIAs within large MRA files, and in doing so, is versatile to user-defined segmentation quality, to detection sensitivity, and across a range of imaging resolutions and modalities. We propose this method as a unique tool to aid UIA screening, characterisation of abnormal vasculature in at-risk patients, morphometry-based rupture risk prediction, and identification of other vascular abnormalities.

CT Angiography-Based Radiomics for Classification of Intracranial Aneurysm Rupture

Background: Intracranial aneurysm rupture is a devastating medical event with a high morbidity and mortality rate. Thus, timely detection and management are critical. The present study aimed to identify the aneurysm radiomics features associated with rupture and to build and evaluate a radiomics classification model of aneurysm rupture. Methods: Radiomics analysis was applied to CT angiography (CTA) images of 393 patients [152 (38.7%) with ruptured aneurysms]. Patients were divided at a ratio of 7:3 into retrospective training (n = 274) and prospective test (n = 119) cohorts. A total of 1,229 radiomics features were automatically calculated from each aneurysm. The feature number was systematically reduced, and the most important classifying features were selected. A logistic regression model was constructed using the selected features and evaluated on training and test cohorts. Radiomics score (Rad-score) was calculated for each patient and compared between ruptured and unruptured aneurysms. Results: Nine radiomics features were selected from the CTA images and used to build the logistic regression model. The radiomics model has shown good performance in the classification of the aneurysm rupture on training and test cohorts [area under the receiver operating characteristic curve: 0.92 [95% confidence interval CI: 0.89-0.95] and 0.86 [95% CI: 0.80-0.93], respectively, p < 0.001]. Rad-score showed statistically significant differences between ruptured and unruptured aneurysms (median, 2.50 vs. -1.60 and 2.35 vs. -1.01 on training and test cohorts, respectively, p < 0.001). Conclusion: The results indicated the potential of aneurysm radiomics features for automatic classification of aneurysm rupture on CTA images.

Improved Depictions of the Anterior Choroidal Artery and Thalamoperforating Arteries on 3D-CTA Images Using Model-based Iterative Reconstruction

RATIONALE AND OBJECTIVES

To evaluate the depictability of intracranial small arteries using high-resolution CTA with model-based iterative reconstruction (MBIR).

MATERIALS AND METHODS

We retrospectively analyzed 21 patients who underwent brain 3D-CTA. Axial and volume-rendered (VR) images were reconstructed from the 3D-CTA raw data using adaptive statistical image reconstruction (ASIR) and MBIR. As a quantitative assessment, intra-arterial CT values of the ICA and contrast-to-noise ratio were measured to evaluate vessel enhancement. Additionally, CT values and standard deviations (SDs) of CT values and signal to noise ratio in white matter parenchyma were measured to evaluate background noise. As a qualitative assessment, the degree of vessel depictability in the anterior choroidal artery (AchoA) and the perforating branches of thalamoperforating arteries (TPA) on VR images using two different reconstruction algorithms was visually evaluated using a 3-point grading system.

RESULTS

The CT value of the ICA [605.27± 89.76 Hounsfield units (HU)] was significantly increased and the SD value (i.e., image noise) of the white matter parenchyma [6.79 ± 0.81(HU)] was decreased on MBIR compared with ASIR [546.76 ± 85.27 (HU)] and [8.04 ± 1.08 HU)] (p <.05 for all). Contrast-to-noise ratio of ICA [84.48 ± 20.17] and signal to noise ratio of white matter [6.18 ± 0.75] with MBIR were significantly higher than ASIR [65.98 ± 13.08] and [5.28 ± 0.78] (p < 0.05 for all). In addition, depictions of the AchoA and TPA on VR images were significantly improved using MBIR compared with ASIR (p < 0.05).

CONCLUSION

MBIR allows depiction of small intracranial arteries such as AchoA and TPA with better visibility than ASIR without increasing the dose of radiation and the amount of contrast agent.

Impact of Virtual Reality in Arterial Anatomy Detection and Surgical Planning in Patients with Unruptured Anterior Communicating Artery Aneurysms

Anterior-communicating artery (ACoA) aneurysms have diverse configurations and anatomical variations. The evaluation and operative treatment of these aneurysms necessitates a perfect surgical strategy based on review of three-dimensional (3D) angioarchitecture using several radiologic imaging methods. We analyzed the influence of 3D virtual reality (VR) reconstructions versus conventional computed tomography angiography (CTA) scans on the identification of vascular anatomy and on surgical planning in patients with unruptured ACoA aneurysms. Medical files were retrospectively analyzed regarding patient- and disease-related data. Preoperative CTA scans were retrospectively reconstructed to 3D-VR images and visualized via VR software to detect the characteristics of unruptured ACoA aneurysms. A questionnaire was used to evaluate the influence of VR on the identification of aneurysm morphology and relevant arterial anatomy and on surgical strategy. Twenty-six patients were included and 520 answer sheets were evaluated. The 3D-VR modality significantly influenced detection of the aneurysm-related vascular structure (p = 0.0001), the recommended head positioning (p = 0.005), and the surgical approach (p = 0.001) in the planning of microsurgical clipping. Thus, reconstruction of conventional preoperative CTA scans into 3D images and the spatial presentation in VR models enabled greater understanding of the anatomy and pathology, provided realistic haptic feedback for aneurysm surgery, and influenced operation planning and strategy.

Deep Learning for Detecting Cerebral Aneurysms with CT Angiography

Background Cerebral aneurysm detection is a challenging task. Deep learning may become a supportive tool for more accurate interpretation. Purpose To develop a highly sensitive deep learning-based algorithm that assists in the detection of cerebral aneurysms on CT angiography images. Materials and Methods Head CT angiography images were retrospectively retrieved from two hospital databases acquired across four different scanners between January 2015 and June 2019. The data were divided into training and validation sets; 400 additional independent CT angiograms acquired between July and December 2019 were used for external validation. A deep learning-based algorithm was constructed and assessed. Both internal and external validation were performed. Jackknife alternative free-response receiver operating characteristic analysis was performed. Results A total of 1068 patients (mean age, 57 years ± 11 [standard deviation]; 660 women) were evaluated for a total of 1068 CT angiograms encompassing 1337 cerebral aneurysms. Of these, 534 CT angiograms (688 aneurysms) were assigned to the training set, and the remaining 534 CT angiograms (649 aneurysms) constituted the validation set. The sensitivity of the proposed algorithm for detecting cerebral aneurysms was 97.5% (633 of 649; 95% CI: 96.0, 98.6). Moreover, eight new aneurysms that had been overlooked in the initial reports were detected (1.2%, eight of 649). With the aid of the algorithm, the overall performance of radiologists in terms of area under the weighted alternative free-response receiver operating characteristic curve was higher by 0.01 (95% CI: 0.00, 0.03). Conclusion The proposed deep learning algorithm assisted radiologists in detecting cerebral aneurysms on CT angiography images, resulting in a higher detection rate. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Kallmes and Erickson in this issue.

A review on the reliability of hemodynamic modeling in intracranial aneurysms: why computational fluid dynamics alone cannot solve the equation

Computational blood flow modeling in intracranial aneurysms (IAs) has enormous potential for the assessment of highly resolved hemodynamics and derived wall stresses. This results in an improved knowledge in important research fields, such as rupture risk assessment and treatment optimization. However, due to the requirement of assumptions and simplifications, its applicability in a clinical context remains limited.This review article focuses on the main aspects along the interdisciplinary modeling chain and highlights the circumstance that computational fluid dynamics (CFD) simulations are embedded in a multiprocess workflow. These aspects include imaging-related steps, the setup of realistic hemodynamic simulations, and the analysis of multidimensional computational results. To condense the broad knowledge, specific recommendations are provided at the end of each subsection.Overall, various individual substudies exist in the literature that have evaluated relevant technical aspects. In this regard, the importance of precise vessel segmentations for the simulation outcome is emphasized. Furthermore, the accuracy of the computational model strongly depends on the specific research question. Additionally, standardization in the context of flow analysis is required to enable an objective comparison of research findings and to avoid confusion within the medical community. Finally, uncertainty quantification and validation studies should always accompany numerical investigations.In conclusion, this review aims for an improved awareness among physicians regarding potential sources of error in hemodynamic modeling for IAs. Although CFD is a powerful methodology, it cannot provide reliable information, if pre- and postsimulation steps are inaccurately carried out. From this, future studies can be critically evaluated and real benefits can be differentiated from results that have been acquired based on technically inaccurate procedures.

Automatic Diagnosis Based on Spatial Information Fusion Feature for Intracranial Aneurysm

Timely and accurate auxiliary diagnosis of intracranial aneurysm can help radiologist make treatment plans quickly, saving lives and cutting costs at the same time. At present, Digital Subtraction Angiography (DSA) is the gold standard for the diagnosis of intracranial aneurysm, but as radiologists interpret those imaging sequences frame by frame, misdiagnosis might occur. The utilization of computer-aided diagnosis (CAD) can ease the burdens of radiologists and improve the detection accuracy of aneurysms. In this article, a deep learning method is applied to detect the intracranial aneurysm in 3D Rotational Angiography (3D-RA) based on a spatial information fusion (SIF) method, and instead of a 3D vascular model, 2D image sequences are used. Given the intracranial aneurysm and vascular overlap having similar feature in the most time, rather than focusing on distinguishing them in one frame, the morphological differences between frames are considered as major feature. In the training data, consecutive frames of every imaging time series are extracted and concatenated in a specific way, so that the spatial contextual information could be embedded into a single two-dimensional image. This method enables the time series with obvious correlation between frames be directly trained on 2D convolutional neural network (CNN), instead of 3D-CNN with huge computational cost. Finally, we got an accuracy of 98.89%, with sensitivity and specificity of 99.38% and 98.19%, respectively, which proves the feasibility and availability of the SIF feature.

Surgical timing in infective endocarditis complicated by intracranial hemorrhage

Given the growing incidence of infective endocarditis (IE), understanding the risks and benefits of valvular surgery is critical. This decision is particularly complex for the 1 in 10 cases complicated by intracranial hemorrhage (ICH). While guideline recommendations currently favor early surgery in general, delayed intervention of at least 4 weeks is still recommended for patients with ICH. To date, there are no randomized controlled trials that inform management of patients with an indication for surgery but concomitant ICH, and even reported observational data are rare. This paper reviews the current literature on timing of surgery with a specific focus on cases of ICH. It emphasizes a growing body of literature challenging the current paradigm that surgery within 4 weeks is associated with neurologic deterioration and high mortality rates by demonstrating favorable outcomes for patients with pre-operative ICH who undergo early valvular surgery. Based on these data, we propose a practical management algorithm to facilitate decisions on surgical timing in these complicated cases. Since more rigorous evidence may never be available, clinicians should make patient-specific surgical timing decisions that attempt to balance the competing risks of neurologic versus cardiac complications.

Comparison of Subtracted Computed Tomography from Computed Tomography Perfusion and Digital Subtraction Angiography in Residue Evaluation of Treated Intracranial Aneurysms

BACKGROUND

Assessing clipped intracranial aneurysms for residues or incomplete occlusions is critical. Digital subtraction angiography (DSA) has been the gold standard for this. Previously, we presented subtracted computed tomography angiography (sub-CTA) from computed tomography perfusion as a more effective noninvasive technique for clipped aneurysms. The aim of this study was to compare effectiveness of sub-CTA with DSA in residue evaluation.

METHODS

A retrospective study of 17 patients with aneurysmal subarachnoid hemorrhage operated on at our institution between November 1, 2016, and December 31, 2018, was performed. Residue aneurysms were evaluated with both sub-CTA and DSA. Positive predictive value and negative predictive value were calculated. Correlation between techniques was determined by the McNemar test and κ value.

RESULTS

Sensitivity of sub-CTA in residue evaluation was low in aneurysms ≤3 mm (positive predictive value = 60%). DSA detected residue aneurysm in 29% (5/17) of patients, whereas sub-CTA detected residue aneurysm in 11% (2/17). Only 40% of aneurysms (2/5) were demonstrated by sub-CTA, all >3 mm; 60% (3/5) were missed, all ≤3 mm.

CONCLUSIONS

This is the first study comparing the effectiveness of sub-CTA from computed tomography perfusion with DSA in residue aneurysm evaluation. Our results were suggestive, but not conclusive. DSA is still the gold standard in residue evaluation. Sub-CTA from computed tomography perfusion can be a reliable method in evaluation of residual aneurysm >3 mm.

Deep Learning-Assisted Diagnosis of Cerebral Aneurysms Using the HeadXNet Model

IMPORTANCE

Deep learning has the potential to augment clinician performance in medical imaging interpretation and reduce time to diagnosis through automated segmentation. Few studies to date have explored this topic.

OBJECTIVE

To develop and apply a neural network segmentation model (the HeadXNet model) capable of generating precise voxel-by-voxel predictions of intracranial aneurysms on head computed tomographic angiography (CTA) imaging to augment clinicians' intracranial aneurysm diagnostic performance.

DESIGN, SETTING, AND PARTICIPANTS

In this diagnostic study, a 3-dimensional convolutional neural network architecture was developed using a training set of 611 head CTA examinations to generate aneurysm segmentations. Segmentation outputs from this support model on a test set of 115 examinations were provided to clinicians. Between August 13, 2018, and October 4, 2018, 8 clinicians diagnosed the presence of aneurysm on the test set, both with and without model augmentation, in a crossover design using randomized order and a 14-day washout period. Head and neck examinations performed between January 3, 2003, and May 31, 2017, at a single academic medical center were used to train, validate, and test the model. Examinations positive for aneurysm had at least 1 clinically significant, nonruptured intracranial aneurysm. Examinations with hemorrhage, ruptured aneurysm, posttraumatic or infectious pseudoaneurysm, arteriovenous malformation, surgical clips, coils, catheters, or other surgical hardware were excluded. All other CTA examinations were considered controls.

MAIN OUTCOMES AND MEASURES

Sensitivity, specificity, accuracy, time, and interrater agreement were measured. Metrics for clinician performance with and without model augmentation were compared.

RESULTS

The data set contained 818 examinations from 662 unique patients with 328 CTA examinations (40.1%) containing at least 1 intracranial aneurysm and 490 examinations (59.9%) without intracranial aneurysms. The 8 clinicians reading the test set ranged in experience from 2 to 12 years. Augmenting clinicians with artificial intelligence-produced segmentation predictions resulted in clinicians achieving statistically significant improvements in sensitivity, accuracy, and interrater agreement when compared with no augmentation. The clinicians' mean sensitivity increased by 0.059 (95% CI, 0.028-0.091; adjusted P = .01), mean accuracy increased by 0.038 (95% CI, 0.014-0.062; adjusted P = .02), and mean interrater agreement (Fleiss κ) increased by 0.060, from 0.799 to 0.859 (adjusted P = .05). There was no statistically significant change in mean specificity (0.016; 95% CI, -0.010 to 0.041; adjusted P = .16) and time to diagnosis (5.71 seconds; 95% CI, 7.22-18.63 seconds; adjusted P = .19).

CONCLUSIONS AND RELEVANCE

The deep learning model developed successfully detected clinically significant intracranial aneurysms on CTA. This suggests that integration of an artificial intelligence-assisted diagnostic model may augment clinician performance with dependable and accurate predictions and thereby optimize patient care.

Use of the stereoscopic virtual reality display system for the detection and characterization of intracranial aneurysms: A Icomparison with conventional computed tomography workstation and 3D rotational angiography

OBJECTIVE

This study aimed to compare the diagnostic performance of the stereoscopic virtual reality display system with the conventional computed tomography (CT) workstation and three-dimensional rotational angiography (3DRA) for intracranial aneurysm detection and characterization, with a focus on small aneurysms and those near the bone.

PATIENTS AND METHODS

First, 42 patients with suspected intracranial aneurysms underwent both 256-row CT angiography (CTA) and 3DRA. Volume rendering (VR) images were captured using the conventional CT workstation. Next, VR images were transferred to the stereoscopic virtual reality display system. Two radiologists independently assessed the results that were obtained using the conventional CT workstation and stereoscopic virtual reality display system. The 3DRA results were considered as the ultimate reference standard.

RESULTS

Based on 3DRA images, 38 aneurysms were confirmed in 42 patients. Two cases were misdiagnosed and 1 was missed when the traditional CT workstation was used. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of the conventional CT workstation were 94.7%, 85.7%, 97.3%, 75%, and99.3%, respectively, on a per-aneurysm basis. The stereoscopic virtual reality display system missed a case. The sensitivity, specificity, PPV, NPV, and accuracy of the stereoscopic virtual reality display system were 100%, 85.7%, 97.4%, 100%, and 97.8%, respectively. No difference was observed in the accuracy of the traditional CT workstation, stereoscopic virtual reality display system, and 3DRA in detecting aneurysms.

CONCLUSION

The stereoscopic virtual reality display system has some advantages in detecting small aneurysms and those near the bone. The virtual reality stereoscopic vision obtained through the system was found as a useful tool in intracranial aneurysm diagnosis and pre-operative 3D imaging.

Updates on Prevention of Cardioembolic Strokes

Cardiac embolism continues to be a leading etiology of ischemic strokes worldwide. Although pathologies that result in cardioembolism have not changed over the past decade, there have been significant advances in the treatment and stroke prevention methods for these conditions. Atrial fibrillation remains the prototypical cause of cardioembolic strokes. The availability of new long-term monitoring devices for atrial fibrillation detection such as insertable cardiac monitors has allowed accurate detection of this leading cause of cardioembolism. The non-vitamin K antagonist oral anticoagulants have improved our ability to prevent strokes for many patients with non-valvular atrial fibrillation (NVAF). Advances in left atrial appendage closure and the U.S. Food and Drug Administration approval of the WATCHMAN (Boston Scientific) device for stroke prevention in NVAF patients who have an appropriate rationale for a nonpharmacological alternative, have revolutionized the field and provided a viable option for patients at higher hemorrhagic risk. The role of patent foramen ovale closure for secondary prevention in selected patients experiencing cryptogenic ischemic strokes at a relatively young age has become clearer thanks to the very recent publication of long-term outcomes from three major studies. Advances in the management of infective endocarditis, heart failure, valvular diseases, and coronary artery disease have significantly changed the management of such patients, but have also revealed new concerns related to assessment of ischemic versus hemorrhagic risk in the setting of antithrombotic use. The current review article aims to discuss these advances especially as they pertain to the stroke neurology practice.

Staged Trapping of Traumatic Basilar Trunk Pseudoaneurysm: Case Report and Review of Literature

BACKGROUND

Traumatic intracranial aneurysms (TICAs) of the posterior circulation in the pediatric populations are rare. Only a few reports in the literature document basilar artery TICA in the pediatric population. These cases were typically associated with a clival fracture and commonly diagnosed weeks to months after trauma. We present a case of a patient with a basilar TICA diagnosed after a motor vehicle collision treated with staged trapping and review of the literature.

CASE DESCRIPTION

We present a case of a 14-year-old boy who sustained a high-speed motor vehicle collision and developed a basilar trunk TICA identified on admission. Initially, the patient underwent craniotomy for proximal sacrifice of the basilar artery in hope for spontaneous thrombosis of the aneurysm through flow reversal. Endovascular options were reviewed and felt to be less feasible than surgical trapping. Due to continued filling through the right posterior communicating artery, the second surgery was performed to distally trap the aneurysm. The aneurysm was opened, showing some thrombosis and the absence of flow. Repeat magnetic resonance imaging did not reveal any new infarction, and the patient was discharged with neurologic improvement over time. At 1 year, he was able to ambulate unassisted and had a modified Rankin Scale score of 3.

CONCLUSION

Development of a TICA may be more acute than literature previously suggested. Treatment consists of a wide range of options and should be considered, especially in the pediatric population, to prevent rupture. Trapping can be performed safely if adequate collateral flow is present in the setting of a large basilar artery aneurysm.