Can noninvasive imaging accurately depict intracranial aneurysms? A systematic review

Impact of an AI software on the diagnostic performance and reading time for the detection of cerebral aneurysms on time of flight MR-angiography

PURPOSE

To evaluate the impact of an AI-based software trained to detect cerebral aneurysms on TOF-MRA on the diagnostic performance and reading times across readers with varying experience levels.

METHODS

One hundred eighty-six MRI studies were reviewed by six readers to detect cerebral aneurysms. Initially, readings were assisted by the CNN-based software mdbrain. After 6 weeks, a second reading was conducted without software assistance. The results were compared to the consensus reading of two neuroradiological specialists and sensitivity (lesion and patient level), specificity (patient level), and false positives per case were calculated for the group of all readers, for the subgroup of physicians, and for each individual reader. Also, reading times for each reader were measured.

RESULTS

The dataset contained 54 aneurysms. The readers had no experience (three medical students), 2 years experience (resident in neuroradiology), 6 years experience (radiologist), and 12 years (neuroradiologist). Significant improvements of overall specificity and the overall number of false positives per case were observed in the reading with AI support. For the physicians, we found significant improvements of sensitivity on lesion and patient level and false positives per case. Four readers experienced reduced reading times with the software, while two encountered increased times.

CONCLUSION

In the reading with the AI-based software, we observed significant improvements in terms of specificity and false positives per case for the group of all readers and significant improvements of sensitivity and false positives per case for the physicians. Further studies are needed to investigate the effects of the AI-based software in a prospective setting.

Shifts in Diagnostic Testing for Headache in the Emergency Department, 2015 to 2021

Importance

Subarachnoid hemorrhage is typically diagnosed by noncontrast head computed tomography (CT); lumbar puncture is recommended if computed tomography is nondiagnostic, although CT cerebral angiography has been promoted as an alternative to lumbar puncture in this diagnostic pathway. The outcomes of this debate in practice have not been studied.

Objective

To determine whether CT cerebral angiography use has increased in lieu of lumbar puncture among emergency department (ED) patients with headache, with an increase in unruptured intracranial aneurysm detection.

Design, Setting, and Participants

This retrospective cohort study took place in 21 community EDs of an integrated health care system in Northern California between 2015 and 2021. Participants were adult (aged >17 years) health plan members with a chief concern of headache. Exclusions were prior diagnoses of subarachnoid hemorrhage, unruptured intracranial aneurysm, cerebral arteriovenous malformation, or cerebrospinal fluid shunt. Data were analyzed from October to November 2023.

Exposures

CT cerebral angiography and/or lumbar puncture during the ED encounter.

Main Outcomes and Measures

Primary and secondary outcomes were 14-day and 90-day unruptured intracranial aneurysm detection, respectively. Safety outcomes were missed diagnoses of subarachnoid hemorrhage or bacterial meningitis. The annual incidence of unruptured intracranial aneurysm detection was normalized to the incidence of subarachnoid hemorrhage (UIA:SAH ratio). Average annualized percentage changes were quantified using joinpoint regression analysis.

Results

Among 198 109 included ED encounters, the mean (SD) age was 47.5 (18.4) years; 140 001 patients (70.7%) were female; 29 035 (14.7%) were Black or African American, 59 896 (30.2%) were Hispanic or Latino, and 75 602 (38.2%) were White. Per year, CT cerebral angiography use increased (18.8%; 95% CI, 17.7% to 20.3%) and lumbar punctures decreased (-11.1%; 95% CI, -12.0% to -10.4%), with a corresponding increase in the 14-day UIA:SAH ratio (3.5%; 95% CI, 0.9% to 7.4%). Overall, computed tomography cerebral angiography use increased 6-fold relative to lumbar puncture, with a 33% increase in the detection of UIA. Results were similar at 90 days and robust to sensitivity analyses. Subarachnoid hemorrhage (1004 cases) and bacterial meningitis (118 cases) were misdiagnosed in 5% and 18% of cases, respectively, with no annual trends (P = .34; z1003 = .95 and P = .74; z117 = -.34, respectively).

Conclusions and Relevance

In this cohort study of ED patients with headache, increases in CT cerebral angiography use were associated with fewer lumbar punctures and higher detection of unruptured intracranial aneurysms, with no significant change in missed diagnoses of subarachnoid hemorrhage or bacterial meningitis. While this shift in diagnostic strategy appeared safe in the short-term, the long-term consequences remain unclear.

A Systematic Review and Case Illustrations of Misdiagnosing Intracranial Aneurysms

Modern neuroimaging methods do not completely rule out false diagnoses of intracranial aneurysms which can lead to an unwarranted operation associated with risks of complications. However, surgical interventions for falsely diagnosed aneurysms are quite rare. The purpose of this study is to demonstrate two clinical cases of false-positive aneurysms and a systematic review of the literature dedicated to the incidence and etiology of false-positive aneurysms, identifying risk factors associated with false-positive aneurysms. A literature search in two databases (PubMed and Web of Science) using keywords "mimicking an intracranial aneurysm", "presenting as an intracranial aneurysm", "false positive intracranial aneurysms", and "neurosurgery" was conducted. A total of 243 papers were found in the initial search in two databases. Sixteen papers (including 20 patients) were included in the final analysis. There were 10 women and 10 men. The most common location of false-positive aneurysms was the bifurcation of the middle cerebral artery (MCA). In the posterior circulation, false-positive aneurysms were identified either on the basilar artery, or at the vertebro-basilar junction. The main causes of false intracranial aneurysm diagnosis included artery occlusion with vascular stump formation, infundibular widening, fenestration, arterial dissection, contrast extravasation, and venous varix. In conclusion, summarizing the results of our analysis, we can say that surgical interventions for false-positive aneurysms are an underestimated problem in vascular neurosurgery. Despite extremely rare published clinical observations, the actual frequency of erroneous surgical interventions for false-positive aneurysms is unknown.

Review Article Imaging Evaluation for the Size of Saccular Intracranial Aneurysm

BACKGROUND

In addition to evaluate the morphologic characteristics of intracranial aneurysms, the dimension of the aneurysm is an important parameter for selecting treatment strategies, determining follow-up period, and predicting the risk of rupture. High-resolution vessel wall imaging has an increasingly dominant role in measuring aneurysm size and assessing the risk of rupture accurately. The size of saccular intracranial aneurysm may play an important role as a predictor of the rupture risk. With the rapid improvement in radiological techniques, different noninvasive imaging methods have respective characteristics in saccular intracranial aneurysms (sIA) measurement and morphologic description. Although most studies believe that the larger the aneurysm, the higher the risk of rupture, there is still a synergistic effect of multiple factors (such as location, morphology, history of aneurysmal subarachnoid hemorrhage, and even patient factors) to explain the rupture of small aneurysms.

METHODS

A literature search was performed of intracranial aneurysm size and risk of rupture.

RESULTS

The specificity and sensitivity of different imaging methods for evaluating intracranial aneurysms varied based on sizes. Rupture risk of aneurysms was associated with multiple factors. A comprehensive assessment that considered aneurysm size in conjunction with other relevant factors would be helpful in guiding options of management.

CONCLUSIONS

Accurate measurement of the dimension of sIA is an important basis in the selection of appropriate treatment including intravascular intervention or surgical clipping, as well as for determining the follow-up cycles for conservative or postoperative treatment. A uniform definition of sIA size is recommended to facilitate the integration of similar studies and to accomplish rapid and effective screening of cases in sIA treatment.

Comparative Study of the Diagnostic Value of Zero-Echo-Time Magnetic Resonance Angiography With Time-of-Flight Magnetic Resonance Angiography for Intracranial Aneurysm

OBJECTIVE

Intracranial aneurysm (IAN) is a class of cerebrovascular diseases with a serious threat to patients, and an accurate diagnosis of IAN is very important for both selection of the appropriate therapy and prediction of the prognosis. This study aimed to evaluate the diagnostic values of zero-echo-time magnetic resonance angiography (ZTE-MRA) and time-of-flight magnetic resonance angiography (TOF-MRA) in patients with IAN.

METHODS

Digital subtraction angiography, ZTE-MRA, and TOF-MRA were performed in 18 patients diagnosed with IAN. The images of ZTE-MRA and TOF-MRA were compared for image quality, qualitative diagnosis, detailed diagnosis, number of thrombi, and residual aneurysm lumen, with digital subtraction angiography as the reference.

RESULTS

Zero-echo-time MRA and TOF-MRA did not show a significant difference in image quality or detailed information (including aneurysm size, growth direction, and angle with the aneurysm-carrying vessel) ( P > 0.05). However, ZTE-MRA showed advantages over TOF-MRA in terms of qualitative diagnosis (sensitivity and specificity), intra-aneurismal thrombus detection, and residual aneurysm lumen detection after embolization ( P < 0.05).

CONCLUSIONS

Compared with TOF-MRA, ZTE-MRA showed greater diagnostic value for IAN patients in terms of qualitative diagnosis, as well as the detection of intra-aneurysm thrombi and residual aneurysm lumen after embolization.

Geometric Deep Learning Using Vascular Surface Meshes for Modality-Independent Unruptured Intracranial Aneurysm Detection

Early detection of unruptured intracranial aneurysms (UIAs) enables better rupture risk and preventative treatment assessment. UIAs are usually diagnosed on Time-of-Flight Magnetic Resonance Angiographs (TOF-MRA) or contrast-enhanced Computed Tomography Angiographs (CTA). Various automatic voxel-based deep learning UIA detection methods have been developed, but these are limited to a single modality. We propose a modality-independent UIA detection method using a geometric deep learning model with high resolution surface meshes of brain vessels. A mesh convolutional neural network with ResU-Net style architecture was used. UIA detection performance was investigated with different input and pooling mesh resolutions, and including additional edge input features (shape index and curvedness). Both a higher resolution mesh (15,000 edges) and additional curvature edge features improved performance (average sensitivity: 65.6%, false positive count/image (FPC/image): 1.61). UIAs were detected in an independent TOF-MRA test set and a CTA test set with average sensitivity of 52.0% and 48.3% and average FPC/image of 1.04 and 1.05 respectively. We provide modality-independent UIA detection using a deep-learning vascular surface mesh model with comparable performance to state-of-the-art UIA detection methods.

Effectiveness of tuning an artificial intelligence algorithm for cerebral aneurysm diagnosis: a study of 10,000 consecutive cases

Diagnostic image analysis for unruptured cerebral aneurysms using artificial intelligence has a very high sensitivity. However, further improvement is needed because of a relatively high number of false positives. This study aimed to confirm the clinical utility of tuning an artificial intelligence algorithm for cerebral aneurysm diagnosis. We extracted 10,000 magnetic resonance imaging scans of participants who underwent brain screening using the "Brain Dock" system. The sensitivity and false positives/case for aneurysm detection were compared before and after tuning the algorithm. The initial diagnosis included only cases for which feedback to the algorithm was provided. In the primary analysis, the sensitivity of aneurysm diagnosis decreased from 96.5 to 90% and the false positives/case improved from 2.06 to 0.99 after tuning the algorithm (P < 0.001). In the secondary analysis, the sensitivity of aneurysm diagnosis decreased from 98.8 to 94.6% and the false positives/case improved from 1.99 to 1.03 after tuning the algorithm (P < 0.001). The false positives/case reduced without a significant decrease in sensitivity. Using large clinical datasets, we demonstrated that by tuning the algorithm, we could significantly reduce false positives with a minimal decline in sensitivity.

Subarachnoid haemorrhage associated with pituitary apoplexy and radiographically occult supraclinoid internal carotid artery aneurysms

In patients with pituitary adenomas, incidental intracranial aneurysms have been documented. Previous studies have highlighted the importance of preoperative imaging in these patients. However, imaging may be limited and fail to show the presence of vascular abnormalities. In this report, we discuss a case of a man in his 30s presenting with a newly diagnosed pituitary adenoma. CT and MRI, on admission, showed a pituitary mass with extension into the right cavernous sinus. After a sudden neurological deterioration, emergent CT/CT angiography revealed pituitary apoplexy with subarachnoid extension without vascular abnormalities. Successful emergency transsphenoidal hypophysectomy was followed by digital subtraction angiography which revealed the presence of two right supraclinoid internal carotid artery aneurysms. With this case, we aim to highlight the need for further vascular imaging in patients with pituitary apoplexy and subarachnoid haemorrhage, as preoperative imaging may be negative for vascular abnormalities especially in the setting of cavernous sinus invasion.

Fenestrated Anterior Communicating Artery Complex Mimicking an Unruptured Aneurysm: Diagnostic Pitfall

Anatomical variations often occur in the anterior communicating artery (AComA) complex, and a careful preoperative evaluation is required before repair of this lesion. We report a case of a fenestrated AComA complex mimicking an unruptured cerebral aneurysm. A 49-year-old woman was referred to our hospital under suspicion of unruptured aneurysms of the AComA and the left middle cerebral artery on magnetic resonance angiography (MRA). Additional three-dimensional computed tomographic angiography (CTA) showed the lesion arising from the AComA complex with a maximum diameter of 4.2 mm. Intraoperative findings showed that the putative aneurysm was actually a fenestrated AComA complex as the blood vessels that formed the AComA complex were dilated and meandering. After the operation, MRA and CTA three-dimensional images were reviewed again but we could still not diagnose the lesion as a fenestrated AComA complex rather than an aneurysm. However, in the MRA source image, a secant line in the lesion was the only finding suggestive of a fenestration. The AComA complex is often associated with various vascular malformations, and it is essential to consider this association in the preoperative evaluation. The interpretation of source images may be helpful for accurate diagnosis and surgical planning.

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.

Imaging of intracranial aneurysms in animals: a systematic review of modalities

Intracranial aneurysm (IA) animal models are paramount to study IA pathophysiology and to test new endovascular treatments. A number of in vivo imaging modalities are available to characterize IAs at different stages of development in these animal models. This review describes existing in vivo imaging techniques used so far to visualize IAs in animal models. We systematically searched for studies containing in vivo imaging of induced IAs in animal models in PubMed and SPIE Digital library databases between 1 January 1945 and 13 July 2022. A total of 170 studies were retrieved and reviewed in detail, and information on the IA animal model, the objective of the study, and the imaging modality used was collected. A variety of methods to surgically construct or endogenously induce IAs in animals were identified, and 88% of the reviewed studies used surgical methods. The large majority of IA imaging in animals was performed for 4 reasons: basic research for IA models, testing of new IA treatment modalities, research on IA in vivo imaging of IAs, and research on IA pathophysiology. Six different imaging techniques were identified: conventional catheter angiography, computed tomography angiography, magnetic resonance angiography, hemodynamic imaging, optical coherence tomography, and fluorescence imaging. This review presents and discusses the advantages and disadvantages of all in vivo IA imaging techniques used in animal models to help future IA studies finding the most appropriate IA imaging modality and animal model to answer their research question.

Advanced cross-sectional imaging of cerebral aneurysms

While the rupture rate of cerebral aneurysms is only 1% per year, ruptured aneurysms are associated with significant morbidity and mortality, while aneurysm treatments have their own associated risk of morbidity and mortality. Conventional markers for aneurysm rupture include patient-specific and aneurysm-specific characteristics, with the development of scoring systems to better assess rupture risk. These scores, however, rely heavily on aneurysm size, and their accuracy in assessing risk in smaller aneurysms is limited. While the individual risk of rupture of small aneurysms is low, due to their sheer number, the largest proportion of ruptured aneurysms are small aneurysms. Conventional imaging techniques are valuable in characterizing aneurysm morphology; however, advanced imaging techniques assessing the presence of inflammatory changes within the aneurysm wall, hemodynamic characteristics of blood flow within aneurysm sacs, and imaging visualization of irregular aneurysm wall motion have been used to further determine aneurysm instability that otherwise cannot be characterized by conventional imaging techniques. The current manuscript reviews conventional imaging techniques and their value and limitations in cerebral aneurysm characterization, and evaluates the applications, value and limitations of advanced aneurysm imaging and post-processing techniques including intracranial vessel wall MRA, 4D-flow, 4D-CTA, and computational fluid dynamic simulations.

Automated Detection of Cerebral Aneurysms on TOF-MRA Using a Deep Learning Approach: An External Validation Study

BACKGROUND AND PURPOSE

Cerebral aneurysms yield the risk of rupture, severe disability and death. Thus, early detection of cerebral aneurysms is crucial to ensure timely treatment, if necessary. AI-based software tools are expected to enhance radiologists' performance in detecting pathologies like cerebral aneurysms in the future. Our aim was to evaluate the diagnostic performance of an artificial intelligence-based software designed to detect intracranial aneurysms on TOF-MRA.

MATERIALS AND METHODS

One hundred ninety-one MR imaging data sets were analyzed using the software mdbrain for the presence of intracranial aneurysms on TOF-MRA obtained using two 3T MR imaging scanners or a 1.5T MR imaging scanner according to our clinical standard protocol. The results were compared with the reading of an experienced radiologist as a criterion standard to measure the sensitivity, specificity, positive and negative predictive values, and accuracy of the software. Additionally, detection rates depending on size, morphology, and location of the aneurysms were evaluated.

RESULTS

Fifty-four aneurysms were detected by the expert reader. The overall sensitivity of the software for the detection of cerebral aneurysms was 72.6%, the specificity was 87.2%, and the accuracy was 82.6%. The positive predictive value was 67.9%, and the negative predictive value was 88.5%. We observed a sensitivity of 100% for saccular aneurysms of >5 mm without signs of thrombosis and low detection rates for fusiform or thrombosed aneurysms of 33.3% and 16.7%, respectively. Of 8 aneurysms that were not included in the initial written reports but were detected by the expert reader, retrospectively, 4 were detected by the software.

CONCLUSIONS

Our data suggest that the software can assist radiologists in reporting TOF-MRA. The software was highly reliable in detecting saccular aneurysms, while for fusiform or thrombosed aneurysms, further improvements are needed. Further studies are necessary to investigate the impact of the software on detection rates, interrater reliability, and reading times.

Imaging Modalities for Intracranial Aneurysm: More Than Meets the Eye

Intracranial aneurysms (IA) are often asymptomatic and have a prevalence of 3 to 5% in the adult population. The risk of IA rupture is low, however when it occurs half of the patients dies from subarachnoid hemorrhage (SAH). To avoid this fatal evolution, the main treatment is an invasive surgical procedure, which is considered to be at high risk of rupture. This risk score of IA rupture is evaluated mainly according to its size and location. Therefore, angiography and anatomic imaging of the intracranial aneurysm are crucial for its diagnosis. Moreover, it has become obvious in recent years that several other factors are implied in this complication, such as the blood flow complexity or inflammation. These recent findings lead to the development of new IA imaging tools such as vessel wall imaging, 4D-MRI, or molecular MRI to visualize inflammation at the site of IA in human and animal models. In this review, we will summarize IA imaging techniques used for the patients and those currently in development.

Radiological investigations in non-aneurysmal subarachnoid haemorrhage: A 5-year review

•

All patients with a Fisher grade 2 bleed and a negative CT angiogram had catheter angiography negative for any abnormality.

•

Neuroradiologists identified vascular abnormalities not reported by district general hospitals.

•

Follow-up MRI may be a useful adjunct in subarachnoid haemorrhage.

The utility of dual-energy computed tomography angiography for the evaluation of brain aneurysms after endovascular coiling: a prospective study

BACKGROUND

Non-invasive alternatives to digital subtraction angiography (DSA) for follow-up of patients with coiled aneurysms are sought.

PURPOSE

To compare a novel method of dual-energy computed tomography angiography (DE-CTA) for postoperative assessment of coiled brain aneurysms to detect aneurysm recanalization and patency of adjacent blood vessels, with DSA.

MATERIAL AND METHODS

Patients who underwent endovascular cerebral aneurysm coiling were prospectively evaluated postoperatively by both DE-CTA and conventional DSA. CTA was performed using a novel dual-energy method with single-source and fast kilovoltage switching. DSA was performed using biplanar cerebral angiography. An experienced neuroradiologist and neurosurgeon, both blinded to the original radiological results, reviewed the images.

RESULTS

A total of 54 patients (16 men, 38 women; mean age=47.6 + 9 years) with 55 coiled aneurysms were enrolled in our study between July 2014 and June 2015: 29 patients had suffered a subarachnoid hemorrhage and 26 patients had an incidentally found cerebral aneurysm. All patients had at least one DSA and DE-CTA performed at most one week apart. DE-CTA showed a 100% sensitivity and specificity in detection of complete aneurysm occlusion and 80% sensitivity and specificity for detection of residual necks and domes. DE-CTA successfully detected all vascular diameter changes as comparable to DSA with minimal interfering artifact.

CONCLUSION

DE-CTA is a promising non-invasive alternative to conventional catheter-based angiography for identification of aneurysm recurrence and assessment of adjacent arteries after endovascular coiling. It allows for far more rapid image acquisition than DSA, is non-invasive, and is widely available at clinical centers.

Formation, Growth, or Rupture of De Novo Intracranial Aneurysms: Long-Term Follow-up Study of Subarachnoid Hemorrhage Survivors

BACKGROUND

The survival rate of aneurysmal subarachnoid hemorrhage (aSAH) has gradually increased, leading to more clinical cases of de novo intracranial aneurysms (DNIAs).

OBJECTIVE

To identify the characteristics of patients with DNIA growth or rupture.

METHODS

We included 1601 patients with aSAH treated by clipping from January 1993 to May 2010. According to the inclusion and exclusion criteria, 233 patients had no DNIAs, and 63 patients had 77 DNIAs. We assessed the incidence rate of DNIAs and risk factors for DNIA formation. After dichotomizing the DNIA group into the heed (patients with DNIA rupture or growth) and stable groups (patients without DNIA growth), we assessed the risk factors for DNIA growth or rupture.

RESULTS

The total follow-up period was 4427.9 patient-years. The incidence rate per patient-year was 1.42%. Age ≤50 yr, family history of aneurysm, and multiplicity at initial aSAH were significant risk factors for DNIA formation. Multivariate regression analysis revealed that female sex (odds ratio [OR], 5.566; 95% confidence interval [CI], 1.241-24.952), duration from initial aSAH to DNIA detection <120 mo (OR, 5.043; 95% CI, 1.362-18.668), multiplicity at initial aSAH (OR, 4.859; 95% CI, 1.207-19.563), and maximum DNIA diameter ≥4 mm (OR, 11.104; 95% CI, 2.337-52.772) were significant risk factors for DNIA growth or rupture.

CONCLUSION

DNIAs had a higher incidence rate than expected. Taking into account the presented incidence rate and risk factors, long-term surveillance in aSAH survivors for more than a decade may be worth considering, at least on a case-by-case basis.

When Is Diagnostic Subtraction Angiography Indicated Before Clipping of Unruptured and Ruptured Intracranial Aneurysms? An International Survey of Current Practice

INTRODUCTION

The goal of this survey is to investigate the indications for preoperative digital subtraction angiography (DSA) before clipping of ruptured and unruptured intracranial aneurysms in an international panel of neurovascular specialists.

METHODS

An anonymous survey of 23 multiple-choice questions relating to indications for DSA before clipping of an intracranial aneurysm was distributed to the international panel of attendees of the European-Japanese Cerebrovascular Congress (EJCVC), which took place in Milan, Italy on 7-9 June 2018. The survey was collected during the same conference. Descriptive statistics were used to analyze the data.

RESULTS

A total of 93 surveys were distributed, and 67 (72%) completed surveys were returned by responders from 13 different countries. Eighty-five percent of all responders were neurosurgeons. For unruptured and ruptured middle cerebral artery (MCA) aneurysms without life-threatening hematoma, approximately 60% of responders perform surgery without preoperative DSA. For aneurysms in other locations than MCA, microsurgery is done without preoperative DSA in 68% of unruptured and in 73% of ruptured cases. In cases of ruptured MCA or ruptured non-MCA aneurysms with life-threatening hematoma, surgery is performed without DSA in 97% and 96% of patients, respectively. Factors which lead to preoperative DSA being performed were: aneurysmal shape (fusiform, dissecting), etiology (infectious), size (>25 mm), possible presence of perforators or efferent vessels arising from the aneurysm, intra-aneurysmal thrombus, previous treatment, location (posterior circulation and paraclinoid aneurysm) and flow-replacement bypass contemplated for final aneurysm treatment. These are all factors that qualify an aneurysm as a complex aneurysm.

CONCLUSION

There is still a high variability in the surgeons' preoperative workup regarding the indication for DSA before clipping of ruptured and unruptured intracranial aneurysms, except for ruptured aneurysms with life-threatening hematoma. There is a general consensus among cerebrovascular specialists that any angioanatomical feature indicating a complex aneurysm should lead to a more detailed workup including preoperative DSA.

Diagnosis and Treatment of Unruptured Intracranial Aneurysms and Aneurysmal Subarachnoid Hemorrhage

Unruptured intracranial aneurysms (UIAs) are commonly acquired vascular lesions that form an outpouching of the arterial wall due to wall thinning. The prevalence of UIAs in the general population is 3.2%. In contrast, an intracranial aneurysm may be manifested after rupture with classic presentation of a thunderclap headache suggesting aneurysmal subarachnoid hemorrhage (SAH). Previous consensus suggests that although small intracranial aneurysms (<7 mm) are less susceptible to rupture, aneurysms larger than 7 mm should be treated on a case-by-case basis with consideration of additional risk factors of aneurysmal growth and rupture. However, this distinction is outdated. The PHASES score, which comprises data pooled from several prospective studies, provides precise estimates by considering not only the aneurysm size but also other variables, such as the aneurysm location. The International Study of Unruptured Intracranial Aneurysms is the largest observational study on the natural history of UIAs, providing the foundation to the current guidelines for the management of UIAs. Although SAH accounts for only 3% of all stroke subtypes, it is associated with considerable burden of morbidity and mortality. The initial management is focused on stabilizing the patient in the intensive care unit with close hemodynamic and serial neurologic monitoring with endovascular or open surgical aneurysm treatment to prevent rebleeding. Since the results of the International Subarachnoid Aneurysm Trial, treatment of aneurysmal SAH has shifted from surgical clipping to endovascular coiling, which demonstrated higher odds of survival free of disability at 1 year after SAH. Nonetheless, aneurysmal SAH remains a public health hazard and is associated with high rates of disability and death.

Clipping of unruptured intracranial aneurysms in patients older than sixty: An age-based analysis

OBJECTIVE

The diagnosis of unruptured intracranial aneurysms (UIAs) is being made more frequently in elderly patients. The goal of this study is to evaluate complications and clinical outcome in patients ≥ 60 years-old who underwent clipping of UIAs.

METHODS

We performed a retrospective cohort study. Clinical outcome (modified Rankin scale score) was determined at the latest clinical follow-up. Complications and outcomes were compared between age groups (60-69, 70-80) and subgroups (60-64, 65-69, 70-74, and >75).

RESULTS

The study population consisted of 255 patients (range 60-80 years-old) who underwent 262 clipping procedures for UIAs. Mean follow-up duration was 15.6 months (± 27.5). Major complications occurred in 20 patients (7.6%) and mortality in 3 patients (1.1%). Medical complications occurred in 26 patients (10%). Mean length of hospital-stay was 4.7 days (± 5.8). 89.6% were discharged to home. 87.8% had a favorable clinical outcome. The 70-80 age group had significantly more complications (P = 0.03) than the 60-69 group and a significantly longer hospital stay (6.02 vs. 4.3 days, P = 0.04). The older group was less likely to discharge to home and more likely to require rehabilitation (P = 0.002). Favorable clinical outcome did not significantly differ between the two groups (85.7% vs. 88.4%, P = 0.56). There was a trend for increasing complications from the younger to older subgroups (P = 0.008) and a reduction in the likelihood to discharge to home (P < 0.0001). The rate of ultimate favorable clinical outcome did not differ significantly between subgroups (P = 0.79).

CONCLUSION

Although complications, length of hospital-stay, and discharge to non-home destinations increase with older age, the majority of patients ≥ 60 may have favorable clinical outcomes.

Computed Tomography Angiography versus Digital Subtraction Angiography as a Primary Diagnostic Tool in Nontraumatic Subarachnoid Hemorrhage: Cost-Effectiveness Analysis Study

BACKGROUND

Digital subtraction angiography (DSA) and computed tomographic angiography (CTA) are used to identify the cause of nontraumatic subarachnoid hemorrhage (SAH). There is no consensus on which to choose as the first diagnostic tool. We aimed to compare the cost-effectiveness of CTA versus DSA as a primary tool for identifying the cause of nontraumatic SAH.

METHODS

A decision analysis model was built to simulate patients undergoing DSA or CTA as a primary diagnostic tool for the cause of nontraumatic SAH. The input data for the study were extracted from literature. Probabilistic and deterministic sensitivity analyses were performed to evaluate the robustness of the model.

RESULTS

In the base case calculation, it cost $1261.82 less and yielded 0.0001 quality-adjusted life year (QALY) when DSA was used as a primary diagnostic imaging tool for nontraumatic SAH. Choosing DSA as a primary tool was cost-effective in more than 65% of iterations in probabilistic sensitivity analysis. Deterministic sensitivity analyses show when the probability of using endovascular treatment is >47.2%, choosing DSA is more cost-effective; otherwise, CTA is more optimal. CTA is more cost-effective when the cost for DSA >2.6 × CTA + $600.

CONCLUSIONS

Based on current literature and our model DSA as a primary diagnostic tool for the cause of nontraumatic SAH is more cost-effective. However, in clinical practice physicians can choose either DSA or CTA according to the scale of endovascular procedures used in their center, as well as the cost correlation between CTA and DSA, which varies among institutions.

Comparing methods of detecting and segmenting unruptured intracranial aneurysms on TOF-MRAS: The ADAM challenge

Accurate detection and quantification of unruptured intracranial aneurysms (UIAs) is important for rupture risk assessment and to allow an informed treatment decision to be made. Currently, 2D manual measures used to assess UIAs on Time-of-Flight magnetic resonance angiographies (TOF-MRAs) lack 3D information and there is substantial inter-observer variability for both aneurysm detection and assessment of aneurysm size and growth. 3D measures could be helpful to improve aneurysm detection and quantification but are time-consuming and would therefore benefit from a reliable automatic UIA detection and segmentation method. The Aneurysm Detection and segMentation (ADAM) challenge was organised in which methods for automatic UIA detection and segmentation were developed and submitted to be evaluated on a diverse clinical TOF-MRA dataset. A training set (113 cases with a total of 129 UIAs) was released, each case including a TOF-MRA, a structural MR image (T1, T2 or FLAIR), annotation of any present UIA(s) and the centre voxel of the UIA(s). A test set of 141 cases (with 153 UIAs) was used for evaluation. Two tasks were proposed: (1) detection and (2) segmentation of UIAs on TOF-MRAs. Teams developed and submitted containerised methods to be evaluated on the test set. Task 1 was evaluated using metrics of sensitivity and false positive count. Task 2 was evaluated using dice similarity coefficient, modified hausdorff distance (95^th percentile) and volumetric similarity. For each task, a ranking was made based on the average of the metrics. In total, eleven teams participated in task 1 and nine of those teams participated in task 2. Task 1 was won by a method specifically designed for the detection task (i.e. not participating in task 2). Based on segmentation metrics, the top two methods for task 2 performed statistically significantly better than all other methods. The detection performance of the top-ranking methods was comparable to visual inspection for larger aneurysms. Segmentation performance of the top ranking method, after selection of true UIAs, was similar to interobserver performance. The ADAM challenge remains open for future submissions and improved submissions, with a live leaderboard to provide benchmarking for method developments at https://adam.isi.uu.nl/.

Prospective Study of Spatial Distribution of Missed Lung Nodules by Readers in CT Lung Screening Using Computer-assisted Detection

PURPOSE

To evaluate the spatial patterns of missed lung nodules in a real-life routine screening environment.

MATERIALS AND METHODS

In a screening institute, 4,822 consecutive adults underwent chest CT, and each image set was independently interpreted by two radiologists in three steps: (1) independently interpreted without computer-assisted detection (CAD) software, (2) independently referred to the CAD results, (3) determined by the consensus of the two radiologists. The locations of nodules and the detection performance data were semi-automatically collected using a CAD server integrated into the reporting system. Fisher's exact test was employed for evaluating findings in different lung divisions. Probability maps were drawn to illustrate the spatial distribution of radiologists' missed nodules.

RESULTS

Radiologists significantly tended to miss lung nodules in the bilateral hilar divisions (p < 0.01). Some radiologists had their own spatial pattern of missed lung nodules.

CONCLUSION

Radiologists tend to miss lung nodules present in the hilar regions significantly more often than in the rest of the lung.

The role of imaging in the management of non-traumatic subarachnoid hemorrhage: a practical review

The purpose of this review is to understand the role of imaging in the diagnosis and management of non-traumatic subarachnoid hemorrhage (SAH). SAH is a life-threatening emergency and a relatively common entity, the most common etiology being ruptured aneurysms. Multiple conundrums exist in literature at various steps of its imaging workup: diagnosis, management, and follow-up. We target our review to highlight the most effective practice and suggest efficient workup plans based on literature search, and describe in detail the clinical diagnostic and prognostic scales, role of CT scan, lumbar puncture, and MR, including angiography in the diagnosis and workup of SAH and its complications, and try to simplify the conundrums. Practical knowledge of imaging workup of SAH can help guide correct management of these patients, so as to reduce morbidity and mortality without resource overutilization.

Sellar Region Lesions and Intracranial Aneurysms in the Era of Endoscopic Endonasal Approach

In the clinical practice of neurosurgery, the endoscopic endonasal approach (EEA) has been the mainstream approach in the management of sellar region diseases. However, clinicians have come to realize that EEA procedure is associated with intraoperative hemorrhage. Due to the limited surgical field and poor proximal control under endoscope, massive hemorrhage always leads to severe complication or even perioperative death. Previously, intraoperative hemorrhage used to be attributed to endoscopic intervention of cavernous sinus or internal carotid artery, but our recent understanding of EEA indicated that preoperatively complicated intracranial aneurysms (IAs) may play a role. In this article, we retrospectively reviewed the baseline characteristics, treatment strategy, pathology, intraoperative findings, as well as radiological profiles of sellar region lesions complicated with IAs. With the focus put on the high comorbidity rate of sellar region lesions and IAs, we did further statistical analysis to sketch the outline of this coexisting circumstance and to emphasize the importance of computed tomography angiography (CTA) as routine EEA preoperative examination. Thorough patient-surgeon communication should be proceeded before the formulation of an individualized treatment strategy.

Can biomechanical analysis shed some light on aneurysmal pathophysiology? Preliminary study on ex vivo cerebral arterial walls

BACKGROUND

The pathophysiology of cerebral aneurysm is complex and poorly understood, and it can have the most catastrophic clinical presentation. Flow dynamics is a key player in the initiation and progression of aneurysm. Better understanding the interaction between hemodynamic loading and biomechanical wall responses can help to add the missing piece on aneurysmal pathophysiology. In this laboratory study we aimed to analyze the effect of the application of a mechanical force to cerebral arterial walls.

METHODS

Displacement control tests were performed on five porcine cerebral arteries. The test machine was the T150 Nanotensile. The stiffness variation with the increment of the strain level is modeled as the outcome of an isotropic hyperelastic material model.

FINDINGS

Through the application of an axial force we obtained Stress/Strain curves that showed a marked isotropic hyperelastic behavior, characterized by an increasing of stiffness with the level of strain. This behavior of the cerebral arterial wall is different from the well-established behavior of other arterial vessel (as the aortic vessel) characterized by a marked anisotropic behavior. Additionally, the data scattering observed for higher values of the applied stress are related to different individual packing of collagen fibers that represent the load-bearing mechanics at higher level of the strain.

INTERPRETATION

The data obtained by test in this paper represent a first step in our ongoing research about the mechanics of multi-axial loads on cerebral arterial walls, and in producing more comprehensive patient-specific calculations for potential applications on cerebral aneurysm management.

Deep Learning Approach for Generating MRA Images From 3D Quantitative Synthetic MRI Without Additional Scans

OBJECTIVES

Quantitative synthetic magnetic resonance imaging (MRI) enables synthesis of various contrast-weighted images as well as simultaneous quantification of T1 and T2 relaxation times and proton density. However, to date, it has been challenging to generate magnetic resonance angiography (MRA) images with synthetic MRI. The purpose of this study was to develop a deep learning algorithm to generate MRA images based on 3D synthetic MRI raw data.

MATERIALS AND METHODS

Eleven healthy volunteers and 4 patients with intracranial aneurysms were included in this study. All participants underwent a time-of-flight (TOF) MRA sequence and a 3D-QALAS synthetic MRI sequence. The 3D-QALAS sequence acquires 5 raw images, which were used as the input for a deep learning network. The input was converted to its corresponding MRA images by a combination of a single-convolution and a U-net model with a 5-fold cross-validation, which were then compared with a simple linear combination model. Image quality was evaluated by calculating the peak signal-to-noise ratio (PSNR), structural similarity index measurements (SSIMs), and high frequency error norm (HFEN). These calculations were performed for deep learning MRA (DL-MRA) and linear combination MRA (linear-MR), relative to TOF-MRA, and compared with each other using a nonparametric Wilcoxon signed-rank test. Overall image quality and branch visualization, each scored on a 5-point Likert scale, were blindly and independently rated by 2 board-certified radiologists.

RESULTS

Deep learning MRA was successfully obtained in all subjects. The mean PSNR, SSIM, and HFEN of the DL-MRA were significantly higher, higher, and lower, respectively, than those of the linear-MRA (PSNR, 35.3 ± 0.5 vs 34.0 ± 0.5, P < 0.001; SSIM, 0.93 ± 0.02 vs 0.82 ± 0.02, P < 0.001; HFEN, 0.61 ± 0.08 vs 0.86 ± 0.05, P < 0.001). The overall image quality of the DL-MRA was comparable to that of TOF-MRA (4.2 ± 0.7 vs 4.4 ± 0.7, P = 0.99), and both types of images were superior to that of linear-MRA (1.5 ± 0.6, for both P < 0.001). No significant differences were identified between DL-MRA and TOF-MRA in the branch visibility of intracranial arteries, except for ophthalmic artery (1.2 ± 0.5 vs 2.3 ± 1.2, P < 0.001).

CONCLUSIONS

Magnetic resonance angiography generated by deep learning from 3D synthetic MRI data visualized major intracranial arteries as effectively as TOF-MRA, with inherently aligned quantitative maps and multiple contrast-weighted images. Our proposed algorithm may be useful as a screening tool for intracranial aneurysms without requiring additional scanning time.

Injection of contrast media using a large-bore angiography catheter with a guidewire in place: Physical factors influencing injection pressure in cerebral angiography

BACKGROUND

We have used a contrast injection scheme termed as "guided catheterization method (guided method)." By using a large-bore 5-Fr catheter and 0.032-in guidewire, a contrast medium could be injected without removing the guidewire. Using a neurovascular phantom, we studied the influence of leaving the guidewire on the contrast injection pressure. Image quality was compared with that obtained using a 4-Fr regular angiography catheter (conventional method).

METHODS

Actual contrast injection pressure, flow rate, flow volume, and several variables from the time-density curve (TDC) were obtained using the guided method and the conventional method. Catheterization parameters included flow rate, the viscosity of a contrast medium (CM), and catheter length. The pressure limit of a contrast injector was set as 1200 psi. Digital subtraction angiography (DSA) images on the neurovascular phantom were acquired. The DSA images were processed, and TDC on a specific region of interest was obtained. Variables from TDC were calculated and compared between the different catheters.

RESULTS

The ranges of actual contrast injection pressure with the conventional and the guided method were 138-299 psi and 184-451 psi, respectively. A minimal reduction of the actual flow rate was found under some conditions with the guided method. Comparable opacifications in DSA images were achieved in all conditions. Although peak intensity was different by flow rate or CM, all TDC variables did not differ based on the catheter. There were no significant harmful events during the 90 experiments.

CONCLUSIONS

With adjustment of the pressure limit, cerebral angiography using the 5-Fr, large-bore catheter without removal of the guidewire is feasible, safe, and expected to provide image quality comparable to that of the 4-Fr regular catheter.

Neurovascular disease, diagnosis, and therapy: Brain aneurysms

Unruptured intracranial aneurysms (UIAs) have a prevalence of 3% in the adult population worldwide. The majority of UIAs are incidental findings, but some UIAs cause cranial nerve palsies, brainstem compression, ischemic events, or epileptic seizures. The most frequent clinical presentation of intracranial aneurysms is, however, rupture and thereby subarachnoid hemorrhage (SAH). To avoid SAH with its fatal consequences, patients with UIAs require counseling by dedicated and interdisciplinary neurovascular specialists. For the purpose of assessment and decision-making for the management of patients with UIAs, numerous aspects have to be considered: radiological characteristics, clinical symptoms, estimated rupture risk of an individual aneurysm as well as patient- and aneurysm-related risks of preventive repair. Generally, two management options exist: observation with follow-up imaging or preventive repair. This chapter discusses current data on pathogenesis, clinical presentation, diagnostics, risk factors for rupture and preventive repair, and guidance tools for the management of patients with UIAs according to current evidence.

Comprehensive review of imaging of intracranial aneurysms and angiographically negative subarachnoid hemorrhage

Intracranial aneurysms confer the risk of subarachnoid hemorrhage (SAH), a potentially devastating condition, though most aneurysms will remain asymptomatic for the lifetime of the patient. Imaging is critical to all stages of patient care for those who harbor an unruptured intracranial aneurysm (UIA), including to establish the diagnosis, to determine therapeutic options, to undertake surveillance in patients who elect not to undergo treatment or whose aneurysm(s) portends such a low risk that treatment is not indicated, and to perform follow-up after treatment. Neuroimaging is equally as important in patients who suffer an SAH. DSA remains the reference standard for imaging of intracranial aneurysms due to its high spatial and temporal resolution. As noninvasive imaging technology, such as CTA and MRA, improves, the diagnostic accuracy of such tests continues to increasingly approximate that of DSA. In cases of angiographically negative SAH, imaging protocols are necessary not only for diagnosis but also to search for an initially occult vascular lesion, such as a thrombosed, ruptured aneurysm that might be detected in a delayed fashion. Given the crucial role of neuroimaging in all aspects of care for patients with UIAs and SAH, it is incumbent on those who care for these patients, including cerebrovascular neurosurgeons, interventional neurologists and neuroradiologists, and diagnostic radiologists and neurointensivists, to understand the role of imaging in this disease and how individual members of the multispecialty team use imaging to ensure best practices to deliver cutting-edge care to these often complex cases. This review expounds on the role of imaging in the management of UIAs and ruptured intracranial aneurysms and in the workup of angiographically negative subarachnoid hemorrhage.

Unruptured Intracranial Aneurysms- Pathogenesis and Individualized Management

BACKGROUND

About 2 million adults in Germany harbor an unruptured intracranial aneurysm (IA). Rupture can lead to a life-threatening subarachnoid hemorrhage. If an IA is detected incidentally in cranial imaging, it must be decided how to proceed.

METHODS

This review includes key publications that were identified by a selective search in the PubMed database using the search term "unruptured intracranial aneurysms," which was performed in July 2019, and based on information obtained from the German Federal Statistical Office on the frequency of the hospital discharge diagnosis "cerebral aneurysm," excluding the diagnosis "subarachnoid hemorrhage," in Germany from 2005 to 2017.

RESULTS

The number of patients in Germany who were admitted or treated for an unruptured IA increased by a factor of 2.3 from 2005 to 2017. The average 5-year rupture risk of approximately 3% must be weighed against the approximately 4% risk associated with an endovascular or microneurosurgical treatment. This emphasizes the need for more precise data on the risk of rupture and for algorithms enabling individualized decision-making for patients with unruptured IA. Risk factors such as IA morphology, arterial hypertension, active smoking, and alcohol consumption (>150 g/week) can markedly increase the risk of rupture, which is generally relatively low. Growing aneurysms are 12 times more likely to rupture than stable ones. Follow-up imaging is thus essential whenever observation rather than intervention is chosen as the initial management.

CONCLUSION

Patients with unruptured IA should be massessed and managed individually. It is also important that risk factors should be treated, if present. Eligible patients are currently being recruited for a phase III clinical trial on the efficacy of blood pressure reduction combined with acetylsalicylic acid intake to counteract inflammatory processes in the arterial wall.

Features of "false positive" unruptured intracranial aneurysms on screening magnetic resonance angiography

BACKGROUND

Physicians can find it challenging to decide whether confirmative digital subtraction angiography (DSA) should be performed in patients who present with "suspicious small aneurysm-like structures" on magnetic resonance angiography (MRA). Factors associated with "false positive aneurysms on MRA" (FPAMs)," which are finally confirmed as negative on DSA, have rarely been reported. This study aimed to identify the clinical or radiologic clues indicative of FPAM on DSA.

METHODS

Patients who had undergone DSA between 2016 and 2019 for suspicious aneurysm-like structures < 5 mm in size on MRA were enrolled. Patient demographics and the details regarding the geometry of the structures were retrospectively reviewed. Univariate and multivariate logistic regression analyses were conducted to identify the associated factors. Receiver operating characteristic curve analysis was performed to assess the clinical implications.

RESULTS

Of the 107 suspicious structures, 46 were indicated as being false positive on DSA (42.96%). Location (positive on C7 and negative on C5-6 ICA) and lower dome to neck ratio were found to be significant parameters in the multivariate analysis. The dome to neck ratio threshold value was 0.99.

CONCLUSION

Suspicious aneurysm-like structures located not on C5-6 but on C7 ICA and having wide neck morphologies (dome to neck ratio < 0.99) are highly likely to be negative on DSA.

Clinical Prediction Score for Early Neuroimaging in Acquired Isolated Oculomotor Nerve Palsy

Purpose

An immediate neuroimaging investigation in patients with isolated oculomotor nerve palsy (ONP) remains controversial. We aimed to develop a clinical prediction score to determine whether or not acquired isolated ONP patients require prompt imaging.

Methods

A retrospective study was performed. Demographic data and clinical presentations were collected to determine predictive factors favored for early brain imaging using multivariate logistic regression analysis.

Results

Ninety-seven eyes of 96 patients diagnosed with isolated ONP were included. Forty-one eyes (42.3%) were caused by ischemia, while the other 56 eyes (57.7%) were caused by non-ischemic etiologies, namely aneurysm (n = 22), trauma (n = 18), inflammation (n = 5), tumor (n = 4), and others (n = 7). Eighty-two eyes (84.5%) had undergone neuroimaging study due to initially suspected non-ischemic causes. Only 36 (43.9%) revealed concordant diagnosis. The potential clinical predictors favored for neuroimaging using multivariate logistic regression analysis were age 10‒50 years (adjusted odds ratio [aOR] 9.01, 95% CI: 1.25‒64.8), age 51‒70 years (aOR 1.71, 95% CI: 0.46‒6.35), history of head trauma (aOR 7.14, 95% CI: 1.19‒42.9), absence of vascular risk factors (aOR 3.85, 95% CI: 1.23‒12.1), and poor pupillary response (aOR 6.96, 95% CI: 1.99‒24.3). The predictor scores with an area under the ROC curve of 0.852 were 4, 1, 4, 3, and 4, respectively. The optimum cut-point was 3 for a sensitivity of 96% and specificity of 44%.

Conclusion

Patients with acquired isolated ONP should be considered early neuroimaging studies when they are younger than 50 years old, have a history of head trauma, have no history of vascular risk factors, or have poor pupillary reaction.

Arterial hypertension in adults. Clinical guidelines 2020

Arterial hypertension in adults. Clinical guidelines 2020

Application of computed tomography angiography for evaluating clinical morphology in intracranial aneurysms - monocentric study

Objective

To examine the clinical effect of computed tomography angiography (CTA) on parameters of intracranial aneurysms in different locations and with different sizes using digital subtraction angiography (DSA) as the standard.

Methods

Patients with intracranial aneurysms who underwent CTA examinations at the same center and received DSA examinations within 3 days were analyzed retrospectively. The morphological parameters of the aneurysms and parent arteries were measured with these two methods.

Results

Mean aneurysm size and parent artery diameter were not different between CTA and DSA. The size of microaneurysms was significantly smaller with DSA than with CTA. The aneurysmal neck width was not different between CTA and DSA. DSA could clearly evaluate the relationship between the aneurysmal neck and the parent artery in all cases. However, CTA had a 90% accuracy rate of visualizing this relationship.

Conclusion

The accuracy rates of evaluating aneurysm size and the aneurysmal neck width and parent artery diameter are similar between CTA and DSA. A DSA examination is essential for evaluating the relationship among microaneurysms, the aneurysmal neck, and the parent artery. CTA is widely applied and more safe in clinical practice, while DSA has a better guiding effect than CTA for some complicated aneurysms.

Four simultaneous anterior cerebral artery aneurysms (three initially unsuspected) with surgical treatment

Distal anterior cerebral artery aneurysms are rare, comprising approximately 6% of all intracranial aneurysms. These aneurysms tend to be smaller in size, broad-based, associated with additional aneurysms and at arterial branching sites, which can make both diagnosis and treatment difficult. Here we report a case of a 63-year-old female who presented with headache and perioral paresthesia determined to be Hunt & Hess scale grade 1. Computed tomography angiography discovered a medium-sized left A2 trunk saccular aneurysm. Intraoperatively 2 additional small blister type aneurysms not noted on initial computed tomography were discovered and treated via clipping and wrapping, respectively. Postoperatively a cerebral angiogram revealed an additional small right A2 trunk broad-based aneurysm. Preoperative evaluation of cerebral vasculature with a cerebral angiogram or high-resolution digital subtraction angiography is essential as multiple aneurysms are commonly associated with anterior cerebral artery aneurysms. The patient was successfully treated without any operative or postoperative complications and has remained symptom-free at 1 year follow up.

Performance of a Deep-Learning Neural Network to Detect Intracranial Aneurysms from 3D TOF-MRA Compared to Human Readers

PURPOSE

To study the clinical potential of a deep learning neural network (convolutional neural networks [CNN]) as a supportive tool for detection of intracranial aneurysms from 3D time-of-flight magnetic resonance angiography (TOF-MRA) by comparing the diagnostic performance to that of human readers.

METHODS

In this retrospective study a pipeline for detection of intracranial aneurysms from clinical TOF-MRA was established based on the framework DeepMedic. Datasets of 85 consecutive patients served as ground truth and were used to train and evaluate the model. The ground truth without annotation was presented to two blinded human readers with different levels of experience in diagnostic neuroradiology (reader 1: 2 years, reader 2: 12 years). Diagnostic performance of human readers and the CNN was studied and compared using the χ²-test and Fishers' exact test.

RESULTS

Ground truth consisted of 115 aneurysms with a mean diameter of 7 mm (range: 2-37 mm). Aneurysms were categorized as small (S; <3 mm; N = 13), medium (M; 3-7 mm; N = 57), and large (L; >7 mm; N = 45) based on the diameter. No statistically significant differences in terms of overall sensitivity (OS) were observed between the CNN and both of the human readers (reader 1 vs. CNN, P = 0.141; reader 2 vs. CNN, P = 0.231). The OS of both human readers was improved by combination of each readers' individual detections with the detections of the CNN (reader 1: 98% vs. 95%, P = 0.280; reader 2: 97% vs. 94%, P = 0.333).

CONCLUSION

A CNN is able to detect intracranial aneurysms from clinical TOF-MRA data with a sensitivity comparable to that of expert radiologists and may have the potential to improve detection rates of incidental findings in a clinical setting.

Meta-analysis of recent literature on utility of follow-up imaging in isolated perimesencephalic hemorrhage

OBJECTIVES

Isolated perimesencephalic subarachnoid hemorrhage is an uncommon, distinct subtype of subarachnoid hemorrhage with a more benign prognosis. A negative computed tomographic angiogram has been shown to be reliable in excluding aneurysmal rupture as the underlying etiology. However, some studies continue advocating for more imaging to determine a vascular cause in perimesencephalic subarachnoid hemorrhage. The objective of this study is to evaluate the evidence for use and utility of repeat angiographic imaging after a negative computed tomographic angiogram in patients with perimesencephalic subarachnoid hemorrhage.

PATIENTS AND METHODS

Retrospective institutional analysis of patients with perimesencephalic subarachnoid hemorrhage was performed from 2014 to 2017 for number and types of follow-up angiographic imaging studies performed. Updated meta-analysis of literature was performed from 2014 onwards to assess the utility of follow-up imaging after a negative initial angiographic study.

RESULTS

The institutional review revealed no utility of additional imaging after a negative computed tomographic angiogram in 6 patients with isolated perimesencephalic subarachnoid hemorrhage. Literature review and metaanalysis of 13 studies with 588 patients revealed a vascular etiology in 3 patients with isolated perimesencephalic subarachnoid hemorrhage from a single study- 2 aneurysms and 1 patient with vasculitis.

CONCLUSIONS

Use of repeat angiographic imaging after a negative computed tomographic angiogram for perimesencephalic subarachnoid hemorrhage patients remains not uncommon, despite previous meta-analysis. Review of the more recent literature is consistent with previously published meta-analysis and shows limited benefits despite frequent use. In patients with a strictly defined perimesencephalic subarachnoid hemorrhage pattern and clinical picture consistent with perimesencephalic subarachnoid hemorrhage, an initial negative computed tomographic angiogram should be adequate and repeated follow-up studies can be avoided.

In vitro accuracy and inter-observer reliability of CT angiography in detecting intracranial aneurysm enlargement

BACKGROUND AND PURPOSE

To evaluate the accuracy and inter-observer variability when CT angiography is used to identify unruptured intracranial aneurysm growth.

METHODS

Two silicone phantom models were used in this study. Each phantom had eight aneurysms of variable size. The size and location of aneurysms in phantom 1 were representative of real patient aneurysms who presented to our institution. Phantom 2 contained aneurysms in the same locations, but with enlargement in various directions. Three blinded board-certified neuroradiologists were asked to identify the size of each aneurysm in three dimensions using CT angiography. The individual enlargement detection rates and inter-observer agreement rates of aneurysm enlargement among the three experts were calculated.

RESULTS

The detection rate of aneurysm enlargement in one dimension was 58.3% among the three observers. Accurate detection of enlargement in all dimensions was 12.5% among the three observers. Detection accuracy was not related to the size of enlargement. Significant inter-observer measurement variability was present.

CONCLUSION

The use of CT angiography was associated with a poor ability to identify aneurysm enlargementaccurately. Further human studies are required to confirm our findings.

Accuracy of detecting enlargement of aneurysms using different MRI modalities and measurement protocols

OBJECTIVE

Aneurysm growth is considered predictive of future rupture of intracranial aneurysms. However, how accurately neuroradiologists can reliably detect incremental aneurysm growth using clinical MRI is still unknown. The purpose of this study was to assess the agreement rate of detecting aneurysm enlargement employing generally used MRI modalities.

METHODS

Three silicone flow phantom models, each with 8 aneurysms of various sizes at different sites, were used in this study. The aneurysm models were identical except for an incremental increase in the sizes of the 8 aneurysms, which ranged from 0.4 mm to 2 mm. The phantoms were imaged on 1.5-T and 3-T MRI units with both time-of-flight (TOF) and contrast-enhanced MR angiography. Three independent expert neuroradiologists measured the aneurysms in a blinded manner using different measurement approaches. The individual and agreement detection rates of aneurysm enlargement among the 3 experts were calculated.

RESULTS

The mean detection rate of any increase in any aneurysmal dimension was 95.7%. The detection rates of the 3 observers (observers A, B, and C) were 98.0%, 96.6%, and 92.7%, respectively (p = 0.22). The detection rates of each MRI modality were 91.3% using 1.5-T TOF, 97.2% using 1.5-T with Gd, 95.8% using 3.0-T TOF, and 97.2% using 3.0-T with Gd (p = 0.31). On the other hand, the mean detection rate for aneurysm enlargement was 54.8%. Specifically, the detection rates of observers A, B, and C were 49.0%, 46.1%, and 66.7%, respectively (p = 0.009). As the incremental enlargement value increased, the detection rate for aneurysm enlargement increased. The use of 1.5-T Gd improved the detection rate for small incremental enlargement (e.g., 0.4–1 mm) of the aneurysm (p = 0.04). The location of the aneurysm also affected the detection rate for aneurysm enlargement (p < 0.0001).

CONCLUSIONS

The detection rate and interobserver agreement were very high for aneurysm enlargement of 0.4–2 mm. The detection rate for at least 1 increase in any aneurysm dimension did not depend on the choice of MRI modality or measurement protocol. Use of Gd improved the accuracy of measurement. Aneurysm location may influence the accuracy of detecting enlargement.

Delayed diagnosis of post-traumatic aneurysm of distal anterior cerebral artery

BACKGROUND

Traumatic intracranial aneurysms (TICA) are often associated with poor prognosis and should be diagnosed as soon as possible to prevent delayed intracranial hemorrhage and high rates of morbidity/mortality related to bleeding. Diagnosis requires a high index of suspicion. The goal of treatment is to exclude the aneurysm issue with surgical or endovascular methods.

CASE DESCRIPTION

We report the case of a 19-year-old boy who suffered a cranio-orbital trauma; 2 weeks after initial trauma he deteriorates with a new intracranial bleeding. Immediate angiography resulted negative. Delayed follow-up by magnetic resonance angiography showed an unruptured aneurysm of anterior cerebral artery that was successfully clipped.

CONCLUSIONS

A TICA should be suspected in case of delayed deterioration in head-injured patient, prompt diagnosis and treatment could improve prognosis and reduce morbidity and mortality.

Deep Learning for MR Angiography: Automated Detection of Cerebral Aneurysms

Purpose To develop and evaluate a supportive algorithm using deep learning for detecting cerebral aneurysms at time-of-flight MR angiography to provide a second assessment of images already interpreted by radiologists. Materials and Methods MR images reported by radiologists to contain aneurysms were extracted from four institutions for the period from November 2006 through October 2017. The images were divided into three data sets: training data set, internal test data set, and external test data set. The algorithm was constructed by deep learning with the training data set, and its sensitivity to detect aneurysms in the test data sets was evaluated. To find aneurysms that had been overlooked in the initial reports, two radiologists independently performed a blinded interpretation of aneurysm candidates detected by the algorithm. When there was disagreement, the final diagnosis was made in consensus. The number of newly detected aneurysms was also evaluated. Results The training data set, which provided training and validation data, included 748 aneurysms (mean size, 3.1 mm ± 2.0 [standard deviation]) from 683 examinations; 318 of these examinations were on male patients (mean age, 63 years ± 13) and 365 were on female patients (mean age, 64 years ± 13). Test data were provided by the internal test data set (649 aneurysms [mean size, 4.1 mm ± 3.2] in 521 examinations, including 177 male patients and 344 female patients with mean age of 66 years ± 12 and 67 years ± 13, respectively) and the external test data set (80 aneurysms [mean size, 4.1 mm ± 2.1] in 67 examinations, including 19 male patients and 48 female patients with mean age of 63 years ± 12 and 68 years ± 12, respectively). The sensitivity was 91% (592 of 649) and 93% (74 of 80) for the internal and external test data sets, respectively. The algorithm improved aneurysm detection in the internal and external test data sets by 4.8% (31 of 649) and 13% (10 of 80), respectively, compared with the initial reports. Conclusion A deep learning algorithm detected cerebral aneurysms in radiologic reports with high sensitivity and improved aneurysm detection compared with the initial reports. © RSNA, 2018 See also the editorial by Flanders in this issue.

Guidelines for radiographic imaging of cranial neuropathies

Disruption of the complex pathways of the 12 cranial nerves can occur at any site along their course, and many, varied pathologic processes may initially manifest as dysfunction and neuropathy. Radiographic imaging (computed topography or magnetic resonance imaging) is frequently used to evaluate cranial neuropathies; however, indications for imaging and imaging method of choice vary considerably between the cranial nerves. The purpose of this review is to provide an analysis of the diagnostic yield and the most clinically appropriate means to evaluate cranial neuropathies using radiographic imaging. Using the PubMed MEDLINE NCBI database, a total of 49,079 articles' results were retrieved on September 20, 2014. Scholarly articles that discuss the etiology, incidence, and use of imaging in the context of evaluation and diagnostic yield of the 12 cranial nerves were evaluated for the purposes of this review. We combined primary research, guidelines, and best practice recommendations to create a practical framework for the radiographic evaluation of cranial neuropathies.