Detection Of Intracranial Aneurysms Research Articles

Automatic detection method of intracranial aneurysms on maximum intensity projection images based on SE-CaraNet

Conventional maximum intensity projection (MIP) images tend to ignore some morphological features in the detection of intracranial aneurysms, resulting in missed detection and misdetection. To solve this problem, a new method for intracranial aneurysm detection based on omni-directional MIP image is proposed in this paper. Firstly, the three-dimensional magnetic resonance angiography (MRA) images were projected with the maximum density in all directions to obtain the MIP images. Then, the region of intracranial aneurysm was prepositioned by matching filter. Finally, the Squeeze and Excitation (SE) module was used to improve the CaraNet model. Excitation and the improved model were used to detect the predetermined location in the omni-directional MIP image to determine whether there was intracranial aneurysm. In this paper, 245 cases of images were collected to test the proposed method. The results showed that the accuracy and specificity of the proposed method could reach 93.75% and 93.86%, respectively, significantly improved the detection performance of intracranial aneurysms in MIP images.

Intracranial aneurysm detection: an object detection perspective.

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. 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. 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. 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.

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

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. 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. 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. CT cerebral angiography and/or lumbar puncture during the ED encounter. 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. 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). 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 deep-learning model for intracranial aneurysm detection on CT angiography images in China: a stepwise, multicentre, early-stage clinical validation study

Artificial intelligence (AI) models in real-world implementation are scarce. Our study aimed to develop a CT angiography (CTA)-based AI model for intracranial aneurysm detection, assess how it helps clinicians improve diagnostic performance, and validate its application in real-world clinical implementation. We developed a deep-learning model using 16 546 head and neck CTA examination images from 14 517 patients at eight Chinese hospitals. Using an adapted, stepwise implementation and evaluation, 120 certified clinicians from 15 geographically different hospitals were recruited. Initially, the AI model was externally validated with images of 900 digital subtraction angiography-verified CTA cases (examinations) and compared with the performance of 24 clinicians who each viewed 300 of these cases (stage 1). Next, as a further external validation a multi-reader multi-case study enrolled 48 clinicians to individually review 298 digital subtraction angiography-verified CTA cases (stage 2). The clinicians reviewed each CTA examination twice (ie, with and without the AI model), separated by a 4-week washout period. Then, a randomised open-label comparison study enrolled 48 clinicians to assess the acceptance and performance of this AI model (stage 3). Finally, the model was prospectively deployed and validated in 1562 real-world clinical CTA cases. The AI model in the internal dataset achieved a patient-level diagnostic sensitivity of 0·957 (95% CI 0·939-0·971) and a higher patient-level diagnostic sensitivity than clinicians (0·943 [0·921-0·961] vs 0·658 [0·644-0·672]; p<0·0001) in the external dataset. In the multi-reader multi-case study, the AI-assisted strategy improved clinicians' diagnostic performance both on a per-patient basis (the area under the receiver operating characteristic curves [AUCs]; 0·795 [0·761-0·830] without AI vs 0·878 [0·850-0·906] with AI; p<0·0001) and a per-aneurysm basis (the area under the weighted alternative free-response receiver operating characteristic curves; 0·765 [0·732-0·799] vs 0·865 [0·839-0·891]; p<0·0001). Reading time decreased with the aid of the AI model (87·5 s vs 82·7 s, p<0·0001). In the randomised open-label comparison study, clinicians in the AI-assisted group had a high acceptance of the AI model (92·6% adoption rate), and a higher AUC when compared with the control group (0·858 [95% CI 0·850-0·866] vs 0·789 [0·780-0·799]; p<0·0001). In the prospective study, the AI model had a 0·51% (8/1570) error rate due to poor-quality CTA images and recognition failure. The model had a high negative predictive value of 0·998 (0·994-1·000) and significantly improved the diagnostic performance of clinicians; AUC improved from 0·787 (95% CI 0·766-0·808) to 0·909 (0·894-0·923; p<0·0001) and patient-level sensitivity improved from 0·590 (0·511-0·666) to 0·825 (0·759-0·880; p<0·0001). This AI model demonstrated strong clinical potential for intracranial aneurysm detection with improved clinician diagnostic performance, high acceptance, and practical implementation in real-world clinical cases. National Natural Science Foundation of China. For the Chinese translation of the abstract see Supplementary Materials section.

Abstract 113: Treatment of Tiny (≤ 3mm) Unruptured Middle Cerebral Artery Aneurysms Are Associated With High Risk of Procedural Complications: An Analysis of the Neurovascular Quality Initiative-Quality Outcomes Database

Introduction: Improved imaging modalities have led to an increased detection of intracranial aneurysms, many of which are small. While studies have shown that many ruptured intracranial aneurysms are small (≤7 mm), the natural history of tiny (≤3 mm) aneurysms, particularly in certain locations such as the middle cerebral artery (MCA) is thought to be relatively benign with a reported rupture rate of less than 0.5% per year. The objective of this study is to evaluate the safety and efficacy of treatment of tiny unruptured MCA aneurysms. Methods: The NVQI-QOD registry was queried for patients with tiny unruptured MCA aneurysms who underwent either microsurgical or endovascular repair. Tiny size was defined as an aneurysm with a maximum dimension of ≤3 mm. Demographics, aneurysm characteristics and treatment safety were queried. Safety data included intra-operative and post-operative complications. Outcomes included modified Rankin Score (mRS) at discharge and last follow up as well as aneurysm occlusion status at discharge. Results: Of 670 treated, unruptured MCA aneurysms, 43 were tiny (6.4%). The mean aneurysm width was 1.9 mm with a mean patient age of 56.3 years. The median pre-operative mRS was 0 (range 0-4). The majority of patients underwent microsurgery (27/43). The overall intra-operative complication rate was 7% (3/43) with an intra-operative rupture rate of 4.7% (2/43). The post-operative complication rate was 9.3% (4/43). New intracerebral hemorrhage occurred in 7% of patients (3/43) and unplanned return to OR occurred in 14.8% of patients who underwent microsurgery (4/27). There were no mortalities. 16.3% (7/43) of patients were discharged to inpatient rehabilitation or a skilled nursing facility. At discharge, 37 (88.1%) patients had complete aneurysm occlusion. In the subgroup of patients with recorded follow up data, only 40% (10/25) had a mRS of 0 at discharge and 40% (6/15) had an mRS of 0 at last follow up (median follow up: 165 days). Conclusions: Our analysis showed that treatment of tiny unruptured MCA aneurysms is associated with a high rate of complications. We suggest that many tiny, unruptured MCA aneurysms should be observed given that the morbidity associated with treatment is likely significantly higher than the risk of rupture.

Advances in research and application of artificial intelligence and radiomic predictive models based on intracranial aneurysm images.

Intracranial aneurysm is a high-risk disease, with imaging playing a crucial role in their diagnosis and treatment. The rapid advancement of artificial intelligence in imaging technology holds promise for the development of AI-based radiomics predictive models. These models could potentially enable the automatic detection and diagnosis of intracranial aneurysms, assess their status, and predict outcomes, thereby assisting in the creation of personalized treatment plans. In addition, these techniques could improve diagnostic efficiency for physicians and patient prognoses. This article aims to review the progress of artificial intelligence radiomics in the study of intracranial aneurysms, addressing the challenges faced and future prospects, in hopes of introducing new ideas for the precise diagnosis and treatment of intracranial aneurysms.

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.

A Systematic Review of Deep-Learning Methods for Intracranial Aneurysm Detection in CT Angiography.

Background: Subarachnoid hemorrhage resulting from cerebral aneurysm rupture is a significant cause of morbidity and mortality. Early identification of aneurysms on Computed Tomography Angiography (CTA), a frequently used modality for this purpose, is crucial, and artificial intelligence (AI)-based algorithms can improve the detection rate and minimize the intra- and inter-rater variability. Thus, a systematic review and meta-analysis were conducted to assess the diagnostic accuracy of deep-learning-based AI algorithms in detecting cerebral aneurysms using CTA. Methods: PubMed (MEDLINE), Embase, and the Cochrane Library were searched from January 2015 to July 2023. Eligibility criteria involved studies using fully automated and semi-automatic deep-learning algorithms for detecting cerebral aneurysms on the CTA modality. Eligible studies were assessed using the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines and the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool. A diagnostic accuracy meta-analysis was conducted to estimate pooled lesion-level sensitivity, size-dependent lesion-level sensitivity, patient-level specificity, and the number of false positives per image. An enhanced FROC curve was utilized to facilitate comparisons between the studies. Results: Fifteen eligible studies were assessed. The findings indicated that the methods exhibited high pooled sensitivity (0.87, 95% confidence interval: 0.835 to 0.91) in detecting intracranial aneurysms at the lesion level. Patient-level sensitivity was not reported due to the lack of a unified patient-level sensitivity definition. Only five studies involved a control group (healthy subjects), whereas two provided information on detection specificity. Moreover, the analysis of size-dependent sensitivity reported in eight studies revealed that the average sensitivity for small aneurysms (<3 mm) was rather low (0.56). Conclusions: The studies included in the analysis exhibited a high level of accuracy in detecting intracranial aneurysms larger than 3 mm in size. Nonetheless, there is a notable gap that necessitates increased attention and research focus on the detection of smaller aneurysms, the use of a common test dataset, and an evaluation of a consistent set of performance metrics.

A deep learning framework for intracranial aneurysms automatic segmentation and detection on magnetic resonance T1 images.

To design a deep learning-based framework for automatic segmentation and detection of intracranial aneurysms (IAs) on magnetic resonance T1 images and test the robustness and performance of framework. A retrospective diagnostic study was conducted based on 159 IAs from 136 patients who underwent the T1 images. Among them, 127 cases were randomly selected for training and validation, and 32 cases were used to assess the accuracy and consistency of our algorithm. We developed and assembled three convolutional neural networks for the segmentation and detection of IAs. The segmentation and detection performance of the model were compared with the ground truth, and various metrics were calculated at the voxel level, IAs level, and patient level to show the performance of our framework. Our assembled model achieved overall Dice, voxel-level sensitivity, specificity, balanced accuracy, and F1 score of 0.802, 0.874, 0.9998, 0.937, and 0.802, respectively. A coincidence greater than 0.7 between the aneurysms predicted by the model and the ground truth was considered as a true positive. For IAs detection, the sensitivity reached 90.63% with 0.58 false positives per case. The volume of IAs segmented by our model showed a high agreement and consistency with the volume of IAs labeled by experts. The deep learning framework is achievable and robust for IAs segmentation and detection. Our model offers more clinical application opportunities compared to digital subtraction angiography (DSA)-based, CTA-based, and MRA-based methods. Our deep learning framework effectively detects and segments intracranial aneurysms using clinical routine T1 sequences, showing remarkable effectiveness and offering great potential for improving the detection of latent intracranial aneurysms and enabling early identification. •There is no segmentation method based on clinical routine T1 images. Our study shows that the proper deep learning framework can effectively localize the intracranial aneurysms. •The T1-based segmentation and detection method is more universal than other angiography-based detection methods, which can potentially reduce missed diagnoses caused by the absence of angiography images. •The deep learning framework is robust and has the potential to be applied in a clinical setting.

Deep geometric learning for intracranial aneurysm detection: towards expert rater performance

BackgroundEarly detection of intracranial aneurysms (IAs) is crucial for patient outcomes. Typically identified on angiographic scans such as CT angiography (CTA) or MR angiography (MRA), the sensitivity of experts in...

Comparison of Ultra-High-Resolution and Normal-Resolution CT-Angiography for Intracranial Aneurysm Detection in Patients with Subarachnoid Hemorrhage

Ruptured intracranial aneurysms (IAs) are the leading cause for atraumatic subarachnoid hemorrhage. In case of aneurysm rupture, patients may face life-threatening complications and require aneurysm occlusion. Detection of the aneurysm in computed tomography (CT) imaging is therefore essential for patient outcome. This study provides an evaluation of the diagnostic accuracy of Ultra-High-Resolution Computed Tomography Angiography (UHR-CTA) and Normal-Resolution Computed Tomography Angiography (NR-CTA) concerning IA detection and characterization. Consecutive patients with atraumatic subarachnoid hemorrhage who received Digital Subtraction Angiography (DSA) and either UHR-CTA or NR-CTA were retrospectively included. Three readers evaluated CT-Angiography regarding image quality, diagnostic confidence and presence of IAs. Sensitivity and specificity were calculated on patient-level and segment-level with reference standard DSA-imaging. CTA patient radiation exposure (effective dose) was compared. One hundred and eight patients were identified (mean age = 57.8 ± 14.1 years, 65 women). UHR-CTA revealed significantly higher image quality and diagnostic confidence (P < 0.001) for all readers and significantly lower effective dose (P < 0.001). Readers correctly classified ≥55/56 patients on UHR-CTA and ≥44/52 patients on NR-CTA. We noted significantly higher patient-level sensitivity for UHR-CTA compared to NR-CTA for all three readers (reader 1: 41/41 [100%] vs. 28/34 [82%], reader 2: 41/41 [100%] vs. 30/34 [88%], reader 3: 41/41 [100%] vs. 30/34 [88%], P ≤ 0.04). Segment-level analysis also revealed significantly higher sensitivity for UHR-CTA compared to NR-CTA for all three readers (reader 1: 47/49 [96%] vs. 34/45 [76%], reader 2: 47/49 [96%] vs. 37/45 [82%], reader 3: 48/49 [98%] vs. 37/45 [82%], P ≤ 0.04). Specificity was comparable for both techniques. We found Ultra-High-Resolution CT-Angiography to provide higher sensitivity than Normal-Resolution CT-Angiography for the detection of intracranial aneurysms in patients with aneurysmal subarachnoid hemorrhage while improving image quality and reducing patient radiation exposure.

Immunoliposomes for detection of rupture-prone intracranial aneurysms

BackgroundIt is estimated that significant (3.2%) of population carries intracranial aneurysm (IA). An increasing number of imaging studies have caused that the chance of finding an incidental aneurysm is becoming more common. Since IA rupture causes subarachnoidal hemorrhage (SAH) and have significant mortality and morbidity prophylactic treatment should be considered when IA is detected. The benefit and risk of treatment of IA is based on epidemiological estimate which takes account patient and aneurysm characteristics. However we know that aneurysm rupture is biological process where inflammation of aneurysm wall is actively leading to degeneration of aneurysm wall and finally weakens it until it bursts. Until now, there have not been imaging method to detect inflammatory process of aneurysm wallMethodsWe created targeting immunoliposome for use in the imaging of aneurysm. Immunoliposome comprises antibodies against at least one vascular inflammatory marker associated with aneurysm inflammation and a label and/or a contrast agent.ResultsHistological analysis of IAs where immunoliposome comprises antibodies against vascular inflammation with a label shows promising results for selectively detecting aneurysms inflammation. In magnetic resonance imaging (MRI) we were able to detect immunoliposomes carrying gadolinium.ConclusionOur work opens a new avenue for using contrast labeled immunoliposomes for detecting rupture-prone aneurysms. Immunoliposomes can cary gadolinium and selectively bind to inflammatory section of aneurysm that can be detected with MRI. Further research is needed to develop immunoliposomes to be used with MRI in humans to target treatment to those patients who benefit from it the most.

Joint two-stage convolutional neural networks for intracranial aneurysms detection on 3D TOF-MRA

Objective. This study aims to develop a three-dimensional convolutional neural network utilizing computer-aided diagnostic technology to facilitate the detection of intracranial aneurysms and automatically assess their location and extent, thereby enhancing the efficiency of radiologists, and streamlining clinical workflows. Approach. A retrospective study was conducted, proposing a joint segmentation and classification network (JSCD-Net) that employs 3D time-of-flight magnetic resonance angiography images for preliminary detection of aneurysms and the minimization of false positives. Specifically, the U-Net++ network was utilized for pre-detection of aneurysms. This was followed by the creation of a multi-path network, co-trained with U-Net++ to correct the results of the first stage to further reduce the rate of false positives. Model effectiveness and robustness were evaluated using sensitivity and false positive analyses on internal and external datasets. A cross-validated free-response receiver operating characteristic curve was also plotted. Main results. JSCD-Net demonstrated a sensitivity of 91.2% (31 of 34; 95% CI: 77.0, 97.0) with an average of 3.55 false positives per scan on the internal test set. For the external test set, it identified 97.2% (70 of 72; 95% CI: 90.4, 99.2) of aneurysms with an average of 2.7 false positives per scan. Significance. When compared with the existing studies, the proposed model shows high sensitivity in detecting intracranial aneurysms with a reasonable number of false positives per case. This result emphasizes the model’s potential as a valuable tool in aiding clinical diagnoses.

Validation of prediction algorithm for risk estimation of intracranial aneurysm development using real-world data

Intracranial aneurysm (IA) is difficult to detect, and most patients remain undiagnosed, as screening tests have potential risks and high costs. Thus, it is important to develop risk assessment system for efficient and safe screening strategy. Through previously published research, we have developed a prediction model for the incidence risk of IA using cohort observational data. This study was designed to verify whether such a prediction model also demonstrates sufficient clinical performance in predicting the prevalence risk at the point of health screening, using cross-sectional data. The study population comprised individuals who visited the Chonnam National University Hwasun Hospital Health Promotion Center in Korea for voluntary medical checkups between 2007 and 2019. All participants had no history of cerebrovascular disease and underwent brain CTA for screening purpose. Presence of IA was evaluated by two specialized radiologists. The risk score was calculated using the previously developed AI model, and 0 point represents the lowest risk and 100 point represents the highest risk. To compare the prevalence according to the risk, age-sex standardization using national database was performed. A study collected data from 5942 health examinations, including brain CTA data, with participants ranging from 20 to 87 years old and a mean age of 52 years. The age-sex standardized prevalence of IA was 3.20%. The prevalence in each risk group was 0.18% (lowest risk, 0–19), 2.12% (lower risk, 20–39), 2.37% (mid-risk, 40–59), 4.00% (higher risk, 60–79), and 6.44% (highest risk, 80–100). The odds ratio between the lowest and highest risk groups was 38.50. The adjusted proportions of IA patients in the higher and highest risk groups were 26.7% and 44.5%, respectively. The median risk scores among IA patients and normal participants were 74 and 54, respectively. The optimal cut-off risk score was 60.5 with an area under the curve of 0.70. We have confirmed that the incidence risk prediction model built through machine learning also shows viable clinical performance in predicting prevalence risk. By utilizing this prediction system, we can effectively predict not only the incidence risk but also the prevalence risk, which is the probability of already having the disease, using health screening data. This may enable us to consider strategies for the early detection of intracranial aneurysms.

A framework for intracranial aneurysm detection and rupture analysis on DSA

BackgroundIntracranial aneurysm is a severe cerebrovascular disease that can result in subarachnoid hemorrhage (SAH), leading to high incidence and mortality rates. Computer-aided detection of aneurysms can assist doctors in enhancing diagnostic accuracy. The analysis of aneurysm imaging holds considerable predictive value for aneurysm rupture. This paper presents a method for the detection of aneurysms and analysis of ruptures using digital subtraction angiography (DSA). MethodsA total of 263 aneurysms were analyzed, with 125 being ruptured and 138 being unruptured. Firstly, a filter based on the eigenvalues of the Hessian matrix was proposed for aneurysm detection. The filter's detection parameters can be automatically obtained through Bayesian optimization. Aneurysms were detected based on their structure and the response of the filter. Secondly, considering the variations in blood flow and morphology among aneurysms in DSA, intensity, texture, and blood perfusion features were extracted from the ruptured aneurysms and unruptured aneurysms. Subsequently, a sparse representation (SR) method was utilized to classify unruptured and ruptured aneurysms. ResultsThe experimental results for aneurysm detection showed that the F1-score was 94.1%. In the classification of ruptured and unruptured aneurysms, the accuracy, sensitivity, specificity, and area under curve (AUC) were 96.1%, 94.4%, 97.5%, and 0.982, respectively. ConclusionThis paper presents a scheme combining an aneurysm detection filter and machine learning, offering a reliable solution for the diagnosis and prediction of aneurysm rupture.

Automated detection of intracranial aneurysms using skeleton-based 3D patches, semantic segmentation, and auxiliary classification for overcoming data imbalance in brain TOF-MRA

Accurate and reliable detection of intracranial aneurysms is vital for subsequent treatment to prevent bleeding. However, the detection of intracranial aneurysms can be time-consuming and even challenging, and there is great variability among experts, especially in the case of small aneurysms. This study aimed to detect intracranial aneurysms accurately using a convolutional neural network (CNN) with 3D time-of-flight magnetic resonance angiography (TOF-MRA). A total of 154 3D TOF-MRA datasets with intracranial aneurysms were acquired, and the gold standards were manually drawn by neuroradiologists. We also obtained 113 subjects from a public dataset for external validation. These angiograms were pre-processed by using skull-stripping, signal intensity normalization, and N4 bias correction. The 3D patches along the vessel skeleton from MRA were extracted. Values of the ratio between the aneurysmal and the normal patches ranged from 1:1 to 1:5. The semantic segmentation on intracranial aneurysms was trained using a 3D U-Net with an auxiliary classifier to overcome the imbalance in patches. The proposed method achieved an accuracy of 0.910 in internal validation and external validation accuracy of 0.883 with a 2:1 ratio of normal to aneurysmal patches. This multi-task learning method showed that the aneurysm segmentation performance was sufficient to be helpful in an actual clinical setting.

3D convolutional neural networks for detecting intracranial aneurysms on brachiocephalic arteries CTA scans

Background: Computed tomography angiography (CTA) is the primary and minimally invasive imaging modality currently used for diagnosis and monitoring of intracranial aneurysms as well as preoperative planning of their treatment. However, its interpretation is time-consuming even for specially trained neuroradiologists. Nowadays little is known whether trained neural networks contribute to analyzing medical images and reduce the time to diagnosis, and how effective they are in detecting intracranial aneurysms according to the CTA findings.Objective: To assess the diagnostic value of a convolutional neural network prototype in the intracranial aneurysm detection according to the brachiocephalic arteries CTA findings.Materials and methods: We analyzed the 3D convolutional neural network prototype based at Kuban State University (Krasnodar, Russian Federation).This prototype was to determine the probability of intracranial aneurysms according to the brachiocephalic arteries CTA findings, obtained in the Radiology Department of Scientific Research Institute – Ochapovsky Regional Clinical Hospital No. 1. The study included 451 CTA scans of 205 patients with confirmed intracranial aneurysms and 246 patients without aneurysms.Results: The sensitivity of the 3D convolutional neural network prototype in the aneurysms detection according to the brachiocephalic arteries CTA findings was 85.1%, the specificity was 95.1%, and the overall accuracy was 91%.Conclusions: The 3D convolutional systems may predict aneurysms with a high accuracy as well as localize them with an accuracy of more than 90%. Such results require a larger dataset.

3D Intracranial Aneurysm Classification and Segmentation Via Unsupervised Dual-Branch Learning.

Intracranial aneurysms are common nowadays and how to detect them intelligently is of great significance in digital health. Whereas most existing deep learning research focused on medical images in a supervised way, we introduce an unsupervised method for the detection of intracranial aneurysms based on 3D point cloud data. In particular, our method consists of two stages: unsupervised pre-training and downstream tasks. As for the former, the main idea is to pair each point cloud with its jittering counterpart and maximise their correspondence. Then we design a dual-branch contrastive network with an encoder for each branch and a subsequent common projection head. As for the latter, we design simple networks for supervised classification and segmentation training. Experiments on the public dataset (IntrA) show that our unsupervised method achieves comparable or even better performance than some state-of-the-art supervised techniques, and it is most prominent in the detection of aneurysmal vessels. Experiments on the ModelNet-40 also show that our method achieves the accuracy of 90.79% which outperforms existing state-of-the-art unsupervised models.

Detection of Intracranial Aneurysms Using Multiphase CT Angiography with a Deep Learning Model

Determine the effect of a multiphase fusion deep-learning model with automatic phase selection in detection of intracranial aneurysm (IA) from computed tomography angiography (CTA) images. CTA images of intracranial arteries from patients at Ningbo First Hospital were retrospectively analyzed. Images were randomly classified as training data, internal validation data, or test data. CTA images from cases examined by digital subtraction angiography (DSA) were examined for independent validation. A deep-learning model was constructed by automatic phase selection of multiphase fusion, and compared to the single-phase algorithm to evaluate algorithm sensitivity. We analyzed 1110 patients (1493 aneurysms) as training data, 139 patients (174 aneurysms) as internal validation data, and 134 patients (175 aneurysms) as test data. The sensitivity of the multiphase analysis of the internal validation data, test data, and independent validation data were greater than from the single-phase analysis. The recall of the multiphase selection was greater or equal to that of single-phase selection in the aneurysm position, shape, size, and rupture status. Use of the test data to determine the presence and absence of aneurysm rupture led to a recall from multiphase selection of 94.8% and 87.6% respectively; both of these values were greater than those from single-phase selection (89.6% and 79.4%). A multiphase fusion deep learning model with automatic phase selection provided automated detection of IAs with high sensitivity.

MRI of unruptured infectious intracranial aneurysms in infective endocarditis. A case-control study

PurposeTo evaluate the usefulness of T2* and FLAIR sequences in the detection of unruptured infectious intracranial aneurysms (UIIAs) in infective endocarditis (IE) including the relationships between the lesion patterns within subarachnoid spaces and the presence of UIIA. MethodsRetrospective review of 15 consecutive patients with definite IE undergoing MR imaging (FLAIR, T2*, DWI, CE-MRA, 3D-T1, CE-3DT1 sequences), in whom DSA detected infectious intracranial aneurysms (IIA). Aneurysmal features (diameter, location, morphology on DSA) and signal patterns onT2*, FLAIR and conventional MR sequences at the site of the UIIA, follow-up MRI and IE background, were analyzed.A control-group of 15 IE-patients without IIA at DSA served for comparison. ResultsAmong 17 UIIAs studied, T2* sequence displayed a susceptibility vessel sign in 15/17 (88.2%), both distal and proximal, which matched with the IIA visualized on DSA. Three patterns of hyposignal areas were identified: (a) signet-ring or target-sign appearance (n = 7), (b) homogeneous, round-, oval- or pear-shaped area (n = 4), and (c) heterogeneous area (n = 4). A FLAIR hyperintensity of the lumen and of the adjacent cortex was present in 6 (35.3%) and 9 (53%) UIIAs, respectively. On T1 (12 UIIAs) a rounded hyposignal (n = 2), within the UIIA lumen matched with the FLAIR hypersignal.Using both T2* and FLAIR had an incremental value with 100% sensitivity and specificity. ConclusionThe susceptibility vessel sign is an MR imaging pattern frequently observed at the site of UIIAs in IE-patients.Both T2* and FLAIR may have the potential to depict UIIAs, regardless of their location and shape.