RESUMEN

Cerebral aneurysms, affecting 2-5% of the global population, are often asymptomatic and commonly located within the Circle of Willis. A recent study in Neurosurgical Review highlights a significant reduction in the annual rupture rates of unruptured cerebral aneurysms (UCAs) in Japan from 2003 to 2018. By analyzing age-adjusted mortality rates of subarachnoid hemorrhage (SAH) and the number of treated ruptured cerebral aneurysms (RCAs), researchers found a substantial decrease in rupture rates-from 1.44 to 0.87% and from 0.92 to 0.76%, respectively (p < 0.001). This 88% reduction was largely attributed to improved hypertension management. Recent advancements in artificial intelligence (AI) and machine learning (ML) further support these findings. The RAPID Aneurysm software demonstrated high accuracy in detecting cerebral aneurysms on CT Angiography (CTA), while ML algorithms showed promise in predicting aneurysm rupture risk. A meta-analysis indicated that ML models could achieve 83% sensitivity and specificity in rupture prediction. Additionally, deep learning techniques, such as the PointNet + + architecture, achieved an AUC of 0.85 in rupture risk prediction. These technological advancements in AI and ML are poised to enhance early detection and risk management, potentially contributing to the observed reduction in UCA rupture rates and improving patient outcomes.

Asunto(s)

RESUMEN

Cerebral aneurysm rupture, the predominant cause of non-traumatic subarachnoid hemorrhage, underscores the need for effective treatment and early detection methods. A study in Neurosurgical Review compared microsurgical clipping to endovascular therapy in 130 patients with middle cerebral artery (MCA) aneurysms, finding significantly fewer serious adverse events (SAEs) and neurological complications in the endovascular group. This suggests endovascular therapy's superiority in safety and reducing complications for MCA aneurysm patients. Furthermore, a systematic review and meta-analysis assessed the diagnostic accuracy of AI algorithms in detecting cerebral aneurysms, revealing a high sensitivity but notable false-positive rates, indicating AI's potential while highlighting the need for further validation. Machine learning algorithms also showed promise in predicting cerebral aneurysm rupture risk, demonstrating reasonable sensitivity and specificity. Additionally, AI-based radiomics models are advancing rapidly, offering enhanced predictive accuracy and personalized treatment planning by analyzing imaging data to identify features indicative of aneurysm conditions. Collectively, these findings emphasize the advantages of endovascular therapy for MCA aneurysms and the emerging role of AI and machine learning in improving early detection and personalized management of cerebral aneurysms.

Asunto(s)

RESUMEN

The letter to the editor titled "Clinical severity of aneurysmal subarachnoid hemorrhage over time: systematic review" provides a comprehensive and systematic examination of the changing clinical landscape of aSAH, emphasizing the importance of advancements in medical technology and treatment protocols. The review's methodological rigor ensures reliable findings, highlighting the positive trends in clinical outcomes due to improved diagnostic tools and early interventions. However, potential publication bias and the need for a more detailed analysis of specific medical innovations and regional variations are notable limitations. Despite these, the letter is a valuable contribution, offering insights that could guide future research and improve patient outcomes.

Asunto(s)

RESUMEN

Intracranial aneurysm (IA) is now a common term closely associated with subarachnoid hemorrhage. IA is the bulging of a blood vessel caused by a weakening of its wall. This bulge can rupture and, in most cases, cause internal bleeding. In most cases, internal bleeding leads to death or other fatal consequences. Therefore, the development of an automated system for detecting IA is needed to help physicians make more accurate diagnoses. For this reason, we have focused on this problem. In this paper, we propose a 2D Convolutional Neural Network (CNN) based on a network commonly used for data classification in medicine. In addition to our proposed network, we also tested ResNet 50, ResNet 101 and ResNet 152 on a publicly available dataset. In this case, ResNet 152 achieved better results than our proposed network, but our network was significantly smaller and the classifications took significantly less time. Our proposed network achieved an overall accuracy of 98%. This result was achieved on a dataset consisting of 611 images. In addition to the mentioned networks, we also experimented with the VGG network, but it was not suitable for this type of data and achieved only 20%. We compare the results in this work with neural networks that have been verified by the scientific community, and we believe that the results obtained by us can help in the creation of an automated system for the detection of IA.

Asunto(s)

RESUMEN

Traumatic intracranial aneurysm (TICA) is a rare and aggressive pathology that requires prompt treatment. Nevertheless, early vascular imaging following head trauma may yield falsely negative results, underscoring the importance of subsequent imaging within the first week to detect delayed TICAs. This study aims to report our experience with delayed TICAs and highlight the clinical importance of repeated angiographic screening for delayed TICAs. In this retrospective analysis, we evaluated patients managed for a TICA at a tertiary care teaching institution over the last decade. Additionally, we conducted a systematic review of the literature, following the PRISMA guidelines, on previously reported TICAs, focusing on the time lag between the injury and diagnosis. Twelve delayed TICAs were diagnosed in 9 patients. The median time interval from injury to diagnosis was 2 days (IQR: 1-22 days), and from diagnosis to treatment was 2 days (IQR: 0-9 days). The average duration of radiological follow-up was 28 ± 38 months. At the final follow-up, four patients exhibited favorable neurological outcomes, while the remainder had adverse outcomes. The mortality rate was 22%. Literature reviews identified 112 patients with 114 TICAs, showcasing a median diagnostic delay post-injury of 15 days (IQR: 6-44 days), with 73% diagnosed beyond the first week post-injury. The median time until aneurysm rupture was 9 days (IQR: 3-24 days). Our findings demonstrate acceptable outcomes following TICA treatment and highlight the vital role of repeated vascular imaging after an initial negative computed tomography or digital subtraction angiography in excluding delayed TICAs.

Asunto(s)

RESUMEN

BACKGROUND: Superficial temporal artery aneurysm is a rare vascular abnormality without specific clinical symptoms. In this case report, we present the case of a patient with superficial temporal artery aneurysm who was diagnosed with migraine headache at first. CASE PRESENTATION: A 60-year-old Iranian man with a previous history of headaches, who did not respond properly to the treatments following the initial diagnosis of migraine, presented with a painless lump in the left temporal region, and he was diagnosed with superficial temporal artery aneurysm via Doppler ultrasound. Finally, surgical removal of the left superficial temporal artery aneurysm was performed. CONCLUSIONS: This case shows the importance of vascular causes in the approach to headache etiologies, especially when the headache is prolonged without proper responses to treatment. Computed tomography angiography and magnetic resonance angiography are appropriate diagnostic methods for aneurysm detection that should be considered in future studies.

Asunto(s)

RESUMEN

RATIONALE: Intracavernous infectious aneurysm (ICIA), represents a rare entity that is always described in the form of case reports in the literature. The coexistence of ICIA and cavernous sinus thrombosis (CST) is extremely rare and poorly understood. PATIENT CONCERNS: A 53-year-old female patient presented to our hospital with headache, nausea and fatigue for 3 weeks. She complained of blurry vision and drooping eyelids before admission. Neurological examination revealed bilateral decreased visual acuity, limitation of extraocular movements and decreased sensation of forehead. Brain magnetic resonance imaging (MRI) showed mixed signal intensities in both cavernous sinuses and expansion of right superior ophthalmic vein, suggesting the formation of CST. One month later, computed tomography angiography (CTA) confirmed a large aneurysm was attached to the left intracavernous carotid artery (ICCA). DIAGNOESE: This patient was diagnosed with ICIA and CST. INTERVENTIONS: She was administered with intravenous meropenem and vancomycin and subcutaneous injection of low molecular heparin for 4 weeks. OUTCOMES: One month later, her extraocular movement had significantly improved, without ptosis and conjunctival congestion. At 1-year follow-up, her ophthalmoplegia fully recovered. Fortunately, such large aneurysm did not rupture in spite of slight broadening. LESSONS: The coexistence of ICIA and CST is extremely rare. Contiguous infection from adjacent tissues is the foremost cause of ICIA. A repeated angiographic examination is recommended under enough anti-infective treatment due to the characteristics of rapid emergence and fast growth of infectious aneurysms.

Asunto(s)

RESUMEN

With the popularization of cerebrovascular imaging technology, the clinical detection rate of unruptured intracranial aneurysm (UIA) is increasing. UIA has a low risk of rupture, but once ruptured, it can seriously affect human health. The treatment of UIA is highly controversial and has attracted widespread clinical attention. The Society of Neurosurgery of the Chinese Medical Association, the Society of Cerebrovascular Surgery of the Chinese Stroke Association, the National Center for Neurological Diseases, and the National Center for Clinical Research on Neurological Diseases jointly formulate "Chinese guideline for the clinical management of patients with unruptured intracranial aneurysm management (2024)", which adopts a modular format, highlighting management recommendations and indicating current research deficiencies and future research directions. It provides comprehensive clinical management recommendations on UIA epidemiology, population screening, clinical imaging and diagnosis, rupture risk assessment, treatment decisions and choices, postoperative follow-up, and long-term management. The evidence sources are divided into the Chinese population and other populations, which helps guide clinical practice in China.

Asunto(s)

RESUMEN

Unruptured intracranial aneurysm (UIA) has an estimated prevalence of about 7% among adults aged 35-75 in China. With the aging population trend, the detection rate of UIA is increasing. Most UIA are incidentally discovered and typically asymptomatic. There has been ongoing debate regarding the choice between aggressive treatment and conservative management. Although UIA has a low annual risk of rupture, once rupture occurs, the mortality and disability rates are high. Based on evidence-based medicine, this clinical management guideline provides 44 recommendations on population screening, clinical imaging diagnosis, risk assessment of growth and rupture, treatment strategies and selection, postoperative follow-up, and management of special populations with UIA. Aiming to provide clinical guidance for clinical doenrs and relevant professionals.

Asunto(s)

RESUMEN

The aim of this study was to investigate the plasma proteome in individuals with intracranial aneurysms (IAs) and identify biomarkers associated with the formation and rupture of IAs. Proteomic profiles (N = 1069 proteins) were assayed in plasma (N = 120) collected from patients with ruptured and unruptured intracranial aneurysms (RIA and UIA), traumatic subarachnoid hemorrhage (tSAH), and healthy controls (HC) using tandem mass tag (TMT) labeling quantitative proteomics analysis. Gene ontology (GO) and pathway analysis revealed that these relevant proteins were involved in immune response and extracellular matrix organization pathways. Seven candidate biomarkers were verified by ELISA in a completely separate cohort for validation (N = 90). Among them, FN1, PON1, and SERPINA1 can be utilized as diagnosis biomarkers of IA, with a combined area under the ROC curve of 0.891. The sensitivity was 93.33%, specificity was 75.86%, and accuracy was 87.64%. PFN1, ApoA-1, and SERPINA1 can serve as independent risk factors for predicting aneurysm rupture. The combined prediction of aneurysm rupture yielded an area under the ROC curve of 0.954 with a sensitivity of 96.15%, specificity of 81.48%, and accuracy of 88.68%. This prediction model was more effective than PHASES score. In conclusion, high-throughput proteomics analysis with population validation was performed to assess blood-based protein expression characteristics. This revealed the potential mechanism of IA formation and rupture, facilitating the discovery of biomarkers. SIGNIFICANCE: Although the annual rupture rate of small unruptured aneurysms is believed to be minimal, studies have indicated that ruptured aneurysms typically have an average size of 6.28 mm, with 71.8% of them being <7 mm in diameter. Hence, evaluating the possibility of rupture in UIA and making a choice between aggressive treatment and conservative observation emerges as a significant challenge in the management of UIA. No biomarker or scoring system has been able to satisfactorily address this issue to date. It would be significant to develop biomarkers that could be used for early diagnosis of IA as well as for prediction of IA rupture. After TMT proteomics analysis and ELISA validation in independent populations, we found that FN1, PON1, and SERPINA1 can be utilized as diagnostic biomarkers for IA, and PFN1, ApoA-1, and SERPINA1 can serve as independent risk factors for predicting aneurysm rupture. Especially, when combined with ApoA-1, SERPINA1, and PFN1 for predicting IA rupture, the area under the curve (AUC) was 0.954 with a sensitivity of 96.15%, specificity of 81.48%, and accuracy of 88.68%. This prediction model was more effective than PHASES score.

Asunto(s)

Asunto(s)

RESUMEN

PURPOSE: To describe a case of combined duplicate origin and early bifurcated middle cerebral artery (MCA) incidentally diagnosed using magnetic resonance (MR) angiography. METHODS: A 51-year-old woman with an unruptured left MCA aneurysm underwent cranial MR angiography with a 3-Tesla scanner for presurgical evaluation. MR angiography was performed using a standard 3-dimensional time-of-flight technique. RESULTS: An unruptured left MCA aneurysm at the M1-M2 junction was identified. The maximum aneurysm diameter was 9 mm. Two almost equally sized right MCAs arose from the terminal segment of the right internal carotid artery. These two channels soon anastomosed, and the temporal branch arose from the inferior channel. The aneurysm was successfully treated with coil embolization. CONCLUSION: We herein report a case of a combined duplicate origin and early bifurcated MCA. This variation can also be regarded as anastomosis between the main MCA and the duplicated MCA. This variation has been previously reported as segmental duplication of the MCA. This is the third case of this rare MCA variation reported in the relevant English-language literature. The term "segmental duplication" may be confused with duplicate origin of the MCA, in which only one artery is located distal to the fusion.

Asunto(s)

RESUMEN

TITLE: Adenoma hemorrágico que imita a un aneurisma de la arteria comunicante anterior.

Asunto(s)

RESUMEN

Aneurysmal subarachnoid hemorrhage (aSAH) can be prevented by early detection and treatment of intracranial aneurysms in high-risk individuals. We investigated whether individuals at high risk of aSAH in the general population can be identified by developing an aSAH prediction model with electronic health records (EHR) data. To assess the aSAH model's relative performance, we additionally developed prediction models for acute ischemic stroke (AIS) and intracerebral hemorrhage (ICH) and compared the discriminative performance of the models. We included individuals aged ≥35 years without history of stroke from a Dutch routine care database (years 2007-2020) and defined outcomes aSAH, AIS and ICH using International Classification of Diseases (ICD) codes. Potential predictors included sociodemographic data, diagnoses, medications, and blood measurements. We cross-validated a Cox proportional hazards model with an elastic net penalty on derivation cohorts and reported the c-statistic and 10-year calibration on validation cohorts. We examined 1,040,855 individuals (mean age 54.6 years, 50.9% women) for a total of 10,173,170 person-years (median 11 years). 17,465 stroke events occurred during follow-up: 723 aSAH, 14,659 AIS, and 2,083 ICH. The aSAH model's c-statistic was 0.61 (95%CI 0.57-0.65), which was lower than the c-statistic of the AIS (0.77, 95%CI 0.77-0.78) and ICH models (0.77, 95%CI 0.75-0.78). All models were well-calibrated. The aSAH model identified 19 predictors, of which the 10 strongest included age, female sex, population density, socioeconomic status, oral contraceptive use, gastroenterological complaints, obstructive airway medication, epilepsy, childbirth complications, and smoking. Discriminative performance of the aSAH prediction model was moderate, while it was good for the AIS and ICH models. We conclude that it is currently not feasible to accurately identify individuals at increased risk for aSAH using EHR data.

Asunto(s)

RESUMEN

PURPOSE: To evaluate the diagnostic efficacy of a developed artificial intelligence (AI) platform incorporating deep learning algorithms for the automated detection of intracranial aneurysms in time-of-flight (TOF) magnetic resonance angiography (MRA). METHOD: This retrospective study encompassed 3D TOF MRA images acquired between January 2023 and June 2023, aiming to validate the presence of intracranial aneurysms via our developed AI platform. The manual segmentation results by experienced neuroradiologists served as the "gold standard". Following annotation of MRA images by neuroradiologists using InferScholar software, the AI platform conducted automatic segmentation of intracranial aneurysms. Various metrics including accuracy (ACC), balanced ACC, area under the curve (AUC), sensitivity (SE), specificity (SP), F1 score, Brier Score, and Net Benefit were utilized to evaluate the generalization of AI platform. Comparison of intracranial aneurysm identification performance was conducted between the AI platform and six radiologists with experience ranging from 3 to 12 years in interpreting MR images. Additionally, a comparative analysis was carried out between radiologists' detection performance based on independent visual diagnosis and AI-assisted diagnosis. Subgroup analyses were also performed based on the size and location of the aneurysms to explore factors impacting aneurysm detectability. RESULTS: 510 patients were enrolled including 215 patients (42.16 %) with intracranial aneurysms and 295 patients (57.84 %) without aneurysms. Compared with six radiologists, the AI platform showed competitive discrimination power (AUC, 0.96), acceptable calibration (Brier Score loss, 0.08), and clinical utility (Net Benefit, 86.96 %). The AI platform demonstrated superior performance in detecting aneurysms with an overall SE, SP, ACC, balanced ACC, and F1 score of 91.63 %, 92.20 %, 91.96 %, 91.92 %, and 90.57 % respectively, outperforming the detectability of the two resident radiologists. For subgroup analysis based on aneurysm size and location, we observed that the SE of the AI platform for identifying tiny (diameter＜3mm), small (3 mm ≤ diameter＜5mm), medium (5 mm ≤ diameter＜7mm) and large aneurysms (diameter ≥ 7 mm) was 87.80 %, 93.14 %, 95.45 %, and 100 %, respectively. Furthermore, the SE for detecting aneurysms in the anterior circulation was higher than that in the posterior circulation. Utilizing the AI assistance, six radiologists (i.e., two residents, two attendings and two professors) achieved statistically significant improvements in mean SE (residents: 71.40 % vs. 88.37 %; attendings: 82.79 % vs. 93.26 %; professors: 90.07 % vs. 97.44 %; P < 0.05) and ACC (residents: 85.29 % vs. 94.12 %; attendings: 91.76 % vs. 97.06 %; professors: 95.29 % vs. 98.82 %; P < 0.05) while no statistically significant change was observed in SP. Overall, radiologists' mean SE increased by 11.40 %, mean SP increased by 1.86 %, and mean ACC increased by 5.88 %, mean balanced ACC promoted by 6.63 %, mean F1 score grew by 7.89 %, and Net Benefit rose by 12.52 %, with a concurrent decrease in mean Brier score declined by 0.06. CONCLUSIONS: The deep learning algorithms implemented in the AI platform effectively detected intracranial aneurysms on TOF-MRA and notably enhanced the diagnostic capabilities of radiologists. This indicates that the AI-based auxiliary diagnosis model can provide dependable and precise prediction to improve the diagnostic capacity of radiologists.

Asunto(s)

Asunto(s)

RESUMEN

OBJECTIVES: Periodic imaging follow-up for patients with unruptured intracranial aneurysms (UIA) is crucial, as studies indicate higher rupture risk with aneurysm growth. However, few studies address patient adherence to follow-up recommendations. This study aims to identify compliance rates and factors influencing follow-up adherence. METHODS: Patients with a UIA were identified from our institution's database from 2011-2021. Follow-up imaging (CT/MR Angiogram) was advised at specific intervals. Patients were categorized into compliant and non-compliant groups based on first-year compliance. Factors contributing to compliance were assessed through multivariate logistic regression. Phone interviews were conducted with non-compliant patients to understand reasons for non-adherence. RESULTS: Among 923 UIA diagnosed patients, 337 were randomly selected for analysis. The median follow-up period was 1.4 years, with a 42% first-year compliance rate. The mean aneurysm size was 3.3 mm. Five patients had a rupture during follow-up, of which 4 died. Compared with patients consulting specialists at the initial diagnosis, those seen by non-specialists exhibited lower compliance (OR 0.25, p < 0.001). Loss to follow-up was greatest during transition from emergency service to specialist appointments. Patients who spoke languages other than English exhibited poorer compliance than those speaking English (OR 0.20, p = 0.01). CONCLUSIONS: Significant amounts of UIA patients at low rupture risk were lost to follow-up before seeing UIA specialists. Main non-compliance factors include inadequate comprehension of follow-up instructions, poor care transfer from non-specialists to specialist, and insurance barriers.

Asunto(s)

RESUMEN

PURPOSE: Intracranial aneurysm detection from 3D Time-Of-Flight Magnetic Resonance Angiography images is a problem of increasing clinical importance. Recently, a streak of methods have shown promising performance by using segmentation neural networks. However, these methods may be less relevant in a clinical settings where diagnostic decisions rely on detecting objects rather than their segmentation. METHODS: We introduce a 3D single-stage object detection method tailored for small object detection such as aneurysms. Our anchor-free method incorporates fast data annotation, adapted data sampling and generation to address class imbalance problem, and spherical representations for improved detection. RESULTS: A comprehensive evaluation was conducted, comparing our method with the state-of-the-art SCPM-Net, nnDetection and nnUNet baselines, using two datasets comprising 402 subjects. The evaluation used adapted object detection metrics. Our method exhibited comparable or superior performance, with an average precision of 78.96%, sensitivity of 86.78%, and 0.53 false positives per case. CONCLUSION: Our method significantly reduces the detection complexity compared to existing methods and highlights the advantages of object detection over segmentation-based approaches for aneurysm detection. It also holds potential for application to other small object detection problems.

Asunto(s)

RESUMEN

BACKGROUND: Intracranial aneurysms (IAs) remain a challenging neurological diagnosis associated with significant morbidity and mortality. There is a plethora of microsurgical and endovascular techniques for the treatment of both ruptured and unruptured aneurysms. There is no definitive consensus as to the best treatment option for this cerebrovascular pathology. The Aneurysm, Arteriovenous Malformation, and Chronic Subdural Hematoma Roundtable Discussion With Industry and Stroke Experts discussed best practices and the most promising approaches to improve the management of brain aneurysms. METHODS: A group of experts from academia, industry, and federal regulators convened to discuss updated clinical trials, scientific research on preclinical system models, management options, screening and monitoring, and promising novel device technologies, aiming to improve the outcomes of patients with IA. RESULTS: Aneurysm, Arteriovenous Malformation, and Chronic Subdural Hematoma Roundtable Discussion With Industry and Stroke Experts suggested the incorporation of artificial intelligence to capture sequential aneurysm growth, identify predictors of rupture, and predict the risk of rupture to guide treatment options. The consensus strongly recommended nationwide systemic data collection of unruptured IA radiographic images for the analysis and development of machine learning algorithms for rupture risk. The consensus supported centers of excellence for preclinical multicenter trials in areas such as genetics, cellular composition, and radiogenomics. Optical coherence tomography and magnetic resonance imaging contrast-enhanced 3T vessel wall imaging are promising technologies; however, more data are needed to define their role in IA management. Ruptured aneurysms are best managed at large volume centers, which should include comprehensive patient management with expertise in microsurgery, endovascular surgery, neurology, and neurocritical care. CONCLUSIONS: Clinical and preclinical studies and scientific research on IA should engage high-volume centers and be conducted in multicenter collaborative efforts. The future of IA diagnosis and monitoring could be enhanced by the incorporation of artificial intelligence and national radiographic and biologic registries. A collaborative effort between academic centers, government regulators, and the device industry is paramount for the adequate management of IA and the advancement of the field.

Asunto(s)

RESUMEN

PURPOSE: The quality and bias of annotations by annotators (e.g., radiologists) affect the performance changes in computer-aided detection (CAD) software using machine learning. We hypothesized that the difference in the years of experience in image interpretation among radiologists contributes to annotation variability. In this study, we focused on how the performance of CAD software changes with retraining by incorporating cases annotated by radiologists with varying experience. METHODS: We used two types of CAD software for lung nodule detection in chest computed tomography images and cerebral aneurysm detection in magnetic resonance angiography images. Twelve radiologists with different years of experience independently annotated the lesions, and the performance changes were investigated by repeating the retraining of the CAD software twice, with the addition of cases annotated by each radiologist. Additionally, we investigated the effects of retraining using integrated annotations from multiple radiologists. RESULTS: The performance of the CAD software after retraining differed among annotating radiologists. In some cases, the performance was degraded compared to that of the initial software. Retraining using integrated annotations showed different performance trends depending on the target CAD software, notably in cerebral aneurysm detection, where the performance decreased compared to using annotations from a single radiologist. CONCLUSIONS: Although the performance of the CAD software after retraining varied among the annotating radiologists, no direct correlation with their experience was found. The performance trends differed according to the type of CAD software used when integrated annotations from multiple radiologists were used.

Asunto(s)