Detection Of Intracranial Aneurysms Research Articles

Application of convolutional network models in detection of intracranial aneurysms: A systematic review and meta-analysis.

Intracranial aneurysms have a high prevalence in human population. It also has a heavy burden of disease and high mortality rate in the case of rupture. Convolutional neural network(CNN) is a type of deep learning architecture which has been proven powerful to detect intracranial aneurysms. Four databases were searched using artificial intelligence, intracranial aneurysms, and synonyms to find eligible studies. Articles which had applied CNN for detection of intracranial aneurisms were included in this review. Sensitivity and specificity of the models and human readers regarding modality, size, and location of aneurysms were sought to be extracted. Random model was the preferred model for analyses using CMA 2 to determine pooled sensitivity and specificity. Overall, 20 studies were used in this review. Deep learning models could detect intracranial aneurysms with a sensitivity of 90/6% (CI: 87/2-93/2%) and specificity of 94/6% (CI: 0/914-0/966). CTA was the most sensitive modality (92.0%(CI:85/2-95/8%)). Overall sensitivity of the models for aneurysms more than 3 mm was above 98% (98%-100%) and 74.6 for aneurysms less than 3 mm. With the aid of AI, the clinicians' sensitivity increased to 12/8% and interrater agreement to 0/193. CNN models had an acceptable sensitivity for detection of intracranial aneurysms, surpassing human readers in some fields. The logical approach for application of deep learning models would be its use as a highly capable assistant. In essence, deep learning models are a groundbreaking technology that can assist clinicians and allow them to diagnose intracranial aneurysms more accurately.

OTO-Net: An Automated MRA Image Segmentation Network for Intracranial Aneurysms.

Intracranial aneurysms are local dilations of the cerebral blood vessels; people with intracranial aneurysms have a high risk to cause bleeding in the brain, which is related to high mortality and morbidity rates. Accurate detection and segmentation of intracranial aneurysms from Magnetic Resonance Angiography (MRA) images are essential in the clinical routine. Manual annotations used to assess the intracranial aneurysms on MRA images are substantial interobserver variability for both aneurysm detection and assessment of aneurysm size and growth. Many prior automated segmentation works have focused their efforts on tackling the problem, but there is still room for performance improvement due to the significant variability of lesions in the location, size, structure, and morphological appearance. To address these challenges, we propose a novel One-Two-One Fully Convolutional Networks (OTO-Net) for intracranial aneurysms automated segmentation in MRA images. The OTO-Net uses full convolution to achieve intracranial aneurysms automated segmentation through the combination of downsampling, upsampling, and skip connection. In addition, loss ensemble is used as the objective function to steadily improve the backpropagation efficiency of the network structure during the training process. We evaluated the proposed OTO-Net on one public benchmark dataset and one private dataset. Our proposed model can achieve the automated segmentation accuracy with 98.37% and 97.86%, average surface distances with 1.081 and 0.753, dice similarity coefficients with 0.9721 and 0.9813, and Hausdorff distance with 0.578 and 0.642 on these two datasets, respectively.

Dense, deep learning-based intracranial aneurysm detection on TOF MRI using two-stage regularized U-Net

Background and purposeThe prevalence of unruptured intracranial aneurysms in the general population is high and aneurysms are usually asymptomatic. Their diagnosis is often fortuitous on MRI and might be difficult and time consuming for the radiologist. The purpose of this study was to develop a deep learning neural network tool for automated segmentation of intracranial arteries and automated detection of intracranial aneurysms from 3D time-of-flight magnetic resonance angiography (TOF-MRA). Materials and methods3D TOF-MRA with aneurysms were retrospectively extracted. All were confirmed with angiography. The data were divided into two sets: a training set of 24 examinations and a test set of 25 examinations. Manual annotations of intracranial blood vessels and aneurysms were performed by neuroradiologists. A double convolutional neuronal network based on the U-Net architecture with regularization was used to increase performance despite a small amount of training data. The performance was evaluated for the test set. Subgroup analyses according to size and location of aneurysms were performed. ResultsThe average processing time was 15 min. Overall, the sensitivity and the positive predictive value of the proposed algorithm were 78% (21 of 27; 95% CI: 62–94) and 62% (21 of 34; 95%CI: 46–78) respectively, with 0.5 FP/case. Despite gradual improvement in sensitivity regarding aneurysm size, there was no significant difference of sensitivity detection between subgroups of size and location. ConclusionsThis developed tool based on a double CNN with regularization trained with small dataset, enables accurate intracranial arteries segmentation as well as effective aneurysm detection on 3D TOF MRA.

Using a Convolutional Neural Network and Convolutional Long Short-term Memory to Automatically Detect Aneurysms on 2D Digital Subtraction Angiography Images: Framework Development and Validation.

BackgroundIt is hard to distinguish cerebral aneurysms from overlapping vessels in 2D digital subtraction angiography (DSA) images due to these images’ lack of spatial information.ObjectiveThe aims of this study were to (1) construct a deep learning diagnostic system to improve the ability to detect posterior communicating artery aneurysms on 2D DSA images and (2) validate the efficiency of the deep learning diagnostic system in 2D DSA aneurysm detection.MethodsWe proposed a 2-stage detection system. First, we established the region localization stage to automatically locate specific detection regions of raw 2D DSA sequences. Second, in the intracranial aneurysm detection stage, we constructed a bi-input+RetinaNet+convolutional long short-term memory (C-LSTM) framework to compare its performance for aneurysm detection with that of 3 existing frameworks. Each of the frameworks had a 5-fold cross-validation scheme. The receiver operating characteristic curve, the area under the curve (AUC) value, mean average precision, sensitivity, specificity, and accuracy were used to assess the abilities of different frameworks.ResultsA total of 255 patients with posterior communicating artery aneurysms and 20 patients without aneurysms were included in this study. The best AUC values of the RetinaNet, RetinaNet+C-LSTM, bi-input+RetinaNet, and bi-input+RetinaNet+C-LSTM frameworks were 0.95, 0.96, 0.92, and 0.97, respectively. The mean sensitivities of the RetinaNet, RetinaNet+C-LSTM, bi-input+RetinaNet, and bi-input+RetinaNet+C-LSTM frameworks and human experts were 89% (range 67.02%-98.43%), 88% (range 65.76%-98.06%), 87% (range 64.53%-97.66%), 89% (range 67.02%-98.43%), and 90% (range 68.30%-98.77%), respectively. The mean specificities of the RetinaNet, RetinaNet+C-LSTM, bi-input+RetinaNet, and bi-input+RetinaNet+C-LSTM frameworks and human experts were 80% (range 56.34%-94.27%), 89% (range 67.02%-98.43%), 86% (range 63.31%-97.24%), 93% (range 72.30%-99.56%), and 90% (range 68.30%-98.77%), respectively. The mean accuracies of the RetinaNet, RetinaNet+C-LSTM, bi-input+RetinaNet, and bi-input+RetinaNet+C-LSTM frameworks and human experts were 84.50% (range 69.57%-93.97%), 88.50% (range 74.44%-96.39%), 86.50% (range 71.97%-95.22%), 91% (range 77.63%-97.72%), and 90% (range 76.34%-97.21%), respectively.ConclusionsAccording to our results, more spatial and temporal information can help improve the performance of the frameworks. Therefore, the bi-input+RetinaNet+C-LSTM framework had the best performance when compared to that of the other frameworks. Our study demonstrates that our system can assist physicians in detecting intracranial aneurysms on 2D DSA images.

Hemodynamics of anterior circulation intracranial aneurysms with daughter blebs: investigating the multidirectionality of blood flow fields

Recent advances in diagnostic neuroradiological imaging, allowed the detection of unruptured intracranial aneurysms (IAs). The shape – irregular or multilobular – of the aneurysmal dome, is considered as a possible rupture risk factor, independently of the size, the location and patient medical background. Disturbed blood flow fields in particular is thought to play a key role in IAs progression. However, there is an absence of widely-used hemodynamic indices to quantify the extent of a multi-directional disturbed flow. We simulated blood flow in twelve patient-specific anterior circulation unruptured intracranial aneurysms with daughter blebs utilizing the spectral/hp element framework Nektar++. We simulated three cardiac cycles using a volumetric flow rate waveform while we considered blood as a Newtonian fluid. To investigate the multidirectionality of the blood flow fields, besides the time-averaged wall shear stress (TAWSS), we calculated the oscillatory shear index (OSI), the relative residence time (RRT) and the time-averaged cross flow index (TACFI). Our CFD simulations suggest that in the majority of our vascular models there is a formation of complex intrasaccular flow patterns, resulting to low and highly oscillating WSS, especially in the area of the daughter blebs. The existence of disturbed multi-directional blood flow fields is also evident by the distributions of the RRT and the TACFI. These findings further support the theory that IAs with daughter blebs are linked to a potentially increased rupture risk.

Interrater and intrarater agreement superior for three-dimensional digital subtraction angiography (3D-DSA) over 2D-DSA classification for detecting remnants after intracranial aneurysm clipping, a GRRAS Reliability and Agreement Study.

Growing evidence suggests that three-dimensional digital subtraction angiography (3D-DSA) is superior to 2D-DSA in detection of intracranial aneurysm (IA) remnants after clipping. With a simple, practical quantitative scale proposed to measure maximal remnant dimension on 3D-DSA, this study provides a rigorous interrater and intrarater reliability and agreement study comparing this newly established scale with a commonly used (Sindou) 2D-DSA scale. Records of 43 patients with clipped IAs harboring various sized remnants who underwent 2D- and 3D-DSA between 2012 and 2018 were evaluated. Using the 2D and 3D scales, six raters scored these remnants and repeated the scoring task 8weeks later. Interrater and intrarater agreement for both grading schemes were calculated using kappa (κ) statistics. Interrater agreement was highly significant, yielding κ-values at 95% CI (p = 0.000) of 0.225 for the first [0.185; 0.265] and 0.368s [0.328; 0.408] time points for 2D-DSA and values of 0.700 for the first [0.654; 0.745] and 0.776s [0.729; 0.822] time points for 3D-DSA. Intrarater agreement demonstrated κ-values between 0.139 and 0.512 for 2D-DSA and between 0.487 and 0.813 for 3D-DSA scores. Interrater and intrarater agreement was minimal or weak for 2D-DSA scores, but strong for 3D-DSA scores. We propose that baseline 3D-DSA characterization may prove more reliable when categorizing clipped IA remnants for purposes of risk stratification and lifelong follow-up.

Artificial intelligence assistance improves the accuracy and efficiency of intracranial aneurysm detection with CT angiography

PurposeThe aim of this study was to evaluate whether a novel head and neck artificial intelligence (AI)-assisted diagnostic system based on a three-dimensional convolutional neural network (3D-CNN) could improve the accuracy, efficiency and working mode of intracranial aneurysm (IA) detection. MethodsA total of 212 patients who underwent computed tomography angiography (CTA) and digital subtraction angiography (DSA) were retrospectively included. We used three diagnostic modes to detect IAs with CTA: AI, physicians and AI + physicians. Taking the diagnostic results of DSA as the gold standard, the sensitivity, specificity, accuracy, mean reporting time, and interobserver consistency of the three diagnostic modes were calculated and compared at the patient and lesion levels. ResultsOf 212 patients, 179 were diagnosed with IAs by DSA, and 224 IAs were analyzed. The sensitivity, specificity and accuracy of the AI system in diagnosing aneurysms were 84.9% (95% confidence interval [CI], 78.9–89.5%), 18.2% (95% CI, 8.2–34.8%) and 74.5% (95% CI, 68.3–80.0%) at the patient-level, and 77.2% (95% CI, 71.3–82.3%), 14.0% (95% CI, 6.2–27.6%) and 67.0% (95% CI, 61.2–72.4%) at the lesion-level, respectively. With AI assistance, junior physicians had the similar diagnostic performance as senior physicians at the patient (sensitivity 95.0% vs. 95.0%, specificity 48.5% vs. 57.6%, accuracy 87.7% vs. 89.2%, p = 0.690) and lesion levels (sensitivity 88.0% vs. 89.7%, specificity 32.0% vs. 38.0%, accuracy 77.8% vs. 80.3%, p = 1.000), especially for aneurysms < 5 mm (sensitivity 83.2% vs. 87.6%, specificity 60.0% vs. 63.2%, accuracy 75.4% vs. 78.9%, p = 0.424). The reporting efficiency of junior and senior physicians improved by 20.7% (141.1 ± 52.6 s to 111.9 ± 46.3 s, p = 0.004) and 18.8% (113.2 ± 42.5 s to 91.9 ± 41.2 s, p = 0.011), respectively. ConclusionsThis 3D-CNN-based AI system significantly improved the accuracy and efficiency of physician detection of IA. The AI + physicians work mode could have a major influence on daily clinical practice and clinical research.

Diagnostic Accuracy of MDCTA for Detection of Intracranial Aneurysm in Non Traumatic Subarachnoid Haemorrhage: A Cross-sectional Study

Introduction: Non Traumatic Subarachnoid Haemorrhage (NTSAH) constitutes a neurological emergency. Multi-Detector Computed Tomographic Angiography (MDCTA) provides significant advantages over Digital Subtraction Angiography (DSA) owing to its immediacy, non invasiveness, and comparable diagnostic accuracy. This warrants exploration of its utility as a fully integrated component of routine imaging and therapeutic algorithm for NTSAH, replacing DSA. Aim: To evaluate the potential of MDCTA of the Circle of Willis (COW) in the detection of causes of NTSAH and compare its diagnostic accuracy with DSA and/or intraoperative findings. Materials and Methods: This cross-sectional study enrolled 45 patients with suspected or confirmed intracranial vascular abnormality or SAH, and subjected to non contrast enhanced Computed Tomography (CT) and MDCTA of the COW. MDCTA findings like aneurysms, Arteriovenous Malformations (AVM), their morphological characteristics and anatomical COW variations were contrasted with DSA/operative findings in 24 patients and MDCTA’s accuracy was calculated. The data was analysed using statistical software R (Ross Ihaka and Robert Gentleman) v.4.0.2, employing Kappa coefficient. The p-value ≤0.05 indicated statistical significance. Results: Total of 45 subjects (mean age: 47.16±17.4 years, 17 females and 28 males) were included in the study. The mean aneurysmal size was 7.6±7.2 mm. Grade 3 or 4 (dense) SAH (48.88%) and aneurysms &lt;3 mm in size (48.89%) were most common. MDCTA showed sensitivity, specificity, and positive and negative predictive values of 89%, 79%, 84% and 85%, respectively. Kappa test revealed a substantial agreement between CTA and DSA (kappa coefficient=0.68). Conclusion: MDCTA is a rapid, minimally invasive, and reliable substitute to DSA in diagnosing and characterising associated aneurysms and AVM, in most cases of NTSAH, aiding in further management of such patients.

Prevalence of asymptomatic unruptured intracranial aneurysm in the elderly Thai population

Subarachnoid hemorrhage is one of the devastating cerebrovascular event. Ruptured intracranial aneurysm is the leading cause of subarachnoid hemorrhage. Early detection of unruptured intracranial aneurysm (UIA) may help prevent subarachnoid hemorrhage. This study aimed to identify the prevalence of asymptomatic UIA among elderly Thai population.

Value of 3D-DSA in the detection of intracranial aneurysms

Aim: To determine the value of three-dimensional (3D) digital subtraction angiography (DSA) in the detection of intracranial aneurysms and to compare 3D technique with DSA. Materials and Methods: A retrospective analysis of 50 patients with 60 intracranial aneurysms who underwent both conventional DSA and 3D-DSA for the evaluation of intracranial aneurysms was conducted. The presence of aneurysms, detection of aneurysmal neck, size, location, presence of additional and small aneurysms analyzed from the two protocols were compared. Results: Three-dimensional technique detected 54 aneurysms while conventional DSA detected 38 aneurysms. There was no correlation between aneurysm detection and aneurysm neck detection in the two technologies observed, but there was a difference in detection performance depending on the technology used. Three-dimensional technique detected 52 aneurysm necks while conventional DSA detected 24 aneurysm necks. There was a statistically significant and positive relationship between the detected size of the aneurysm using 3D technique and DSA technology. Three-dimensional technique detected 24 additional aneurysms while conventional DSA detected only six additional aneurysms. Conclusions: Three-dimensional technique are more successful in the detection of aneurysms, their necks and small aneurysms in comparison to digital subtraction angiography, but difference is not statistically significant. The size of the aneurysm statistically significant affects the aneurysm neck detection by conventional DSA.

Efficient Synthesis of Water-Soluble Magnetic Nanoparticles and Its Application in MRI in the Detection of Intracranial Aneurysm

Magnetic nanoparticles were used in medical images, which could further improve image clarity, while watersoluble nanoparticles put forward more new requirements for the biocompatibility of nanoparticles. This research adopted a simple and novel method to prepare water-soluble iron oxide nanoparticles. First, transmission electron microscope (TEM) was used to analyze the size distribution of the prepared product; X-ray diffraction (XRD) was used to test the crystal structure of the prepared sample; the fast Fourier transform (FFT) spectrum was introduced to analyze the structural properties of the nanoparticles; the nanoparticle aqueous solutions of different concentrations were designed, and the impact of water-soluble nanoparticles on magnetic resonance imaging (MRI) was examined with the nuclear magnetic resonance spectrometer. At the same time, the prepared water-soluble nanoparticle solution was used for high-resolution tumor wall imaging of patients with unruptured intracranial aneurysm (IA) to compare the imaging effect of the aneurysm wall before and after the introduction of nanoparticles. In the material characterization test of nanoparticles, the prepared samples did not have certain iron oxide characteristic peaks, which means the synthesized iron oxide nanoparticles did not have a fixed crystal morphology. The samples tested by energy dispersive spectrometer (EDS) also contained Fe, O, C and Na. The average particle size was 5.8 nm. It was found under high-resolution TEM that the particle mirror spacing was 0.48 nm, which was consistent with the 111-crystal plane of Fe3O4; The magnetic hysteresis loop test confirmed that when the concentration of nanoparticles increased, the solution would form a magnetic fluid. When the concentration of aqueous solution of nanoparticles increased, the corresponding MRI signal would be significantly enhanced. It was used in the MR scan of patients with unruptured IA. Nanoparticle solution could increase the visibility of the aneurysm, and the image quality of the aneurysm wall could be significantly enhanced.

Factors Associated with Subsequent Subarachnoid Hemorrhages in Patients with Multiple Intracranial Aneurysms

Detection of multiple intracranial aneurysms (MIAs) in patients with aneurysmal subarachnoid hemorrhage (aSAH) is common and the optimal management of the additional unruptured intracranial aneurysms (UIA) is often a matter of debate. We calculate the incidence and the factors associated with subsequent aSAHs from untreated additional aneurysms in a single-center group of patients with aSAH and MIAs. Charts of patients with MIAs admitted to our neurosurgery department for aSAH between January 2000 and March 2020 were retrospectively reviewed. Incidence rate and factors associated with subsequent aSAHs were calculated with univariable and multivariable analyses. Of the unruptured aneurysms, 50% were preventively treated. During a median follow-up of 3 years, 20 of 174 patients (11.5%) presented with a second aSAH. Incidence of rupture of an additional untreated aneurysm was 18.05 per 1000 person/years (confidence interval, 10.69-30.47). Rupture incidence of an additional aneurysm located in the anterior circulation was 32.70 per 1000 person/years and 40.73 per 1000 person/years in the posterior circulation. Presence of untreated mirror and de novo aneurysms increased the risk of overall subsequent aSAHs by 16.9-fold and 7.6-fold, respectively. Most untreated additional aneurysms causing a subsequent aSAH were smaller than 7 mm (73.3%), with middle cerebral artery being the most frequent location (40.0%). Incidence of subsequent aSAHs is high in patients with aSAH-MIA. Untreated mirror and de novo aneurysms are associated with higher rupture risk. Longer follow-up and prophylactic treatment of asymptomatic aneurysms at higher rupture risk are recommended to prevent the significant poor outcome of subsequent aSAHs.

Screening for cerebrovascular disorder on the basis of family history in asymptomatic children

Background: Cerebrovascular disorders represent a group of uncommon, heterogeneous, and complex conditions in children. We reviewed the screening practice for the detection of cerebrovascular disorder in asymptomatic children referred to our neurovascular service on the basis of a positive family history and parental and/or treating physician concern. Methods: Retrospective case-note review of referrals to our neurovascular service (July 2008–April 2018). Patients were included if the referral was made for screening, on the basis of a positive family history of cerebrovascular disorder. Symptomatic children, those with previous cranial imaging, or children under the care of a clinical geneticist (i.e. due to the child or their relative having HHT or mutations in KRIT1) were not eligible for inclusion. Results: Forty-one children were reviewed, 22 males (Median age 10.7 years, range 0.6–15.6 years). This represented 22% of the total number of referrals over a 10-year period. Twenty-nine children had an MRI/MRA brain. Twenty-eight children were referred due to a family history of intracranial aneurysm and/or subarachnoid haemorrhage, but only two had two first-degree relatives affected. Ten children were referred due to a family history of arteriovenous malformation. Three children were referred due to a family history of stroke. No cerebrovascular disease was detected during the study period (n = 29). Conclusions: Parental and/or physician concern generated a substantial number of referrals but no pathology was detected after screening. Whilst general screening guidance exists for the detection of intracranial aneurysms, consensus guidelines for the screening of children with a positive family history do not, but are required both to guide clinical practice and to assuage parental and/or physician concerns.

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 (95th 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/.

Deep neural network-based detection and segmentation of intracranial aneurysms on 3D rotational DSA.

Accurate diagnosis and measurement of intracranial aneurysms are challenging. This study aimed to develop a 3D convolutional neural network (CNN) model to detect and segment intracranial aneurysms (IA) on 3D rotational DSA (3D-RA) images. 3D-RA images were collected and annotated by 5 neuroradiologists. The annotated images were then divided into three datasets: training, validation, and test. A 3D Dense-UNet-like CNN (3D-Dense-UNet) segmentation algorithm was constructed and trained using the training dataset. Diagnostic performance to detect aneurysms and segmentation accuracy was assessed for the final model on the test dataset using the free-response receiver operating characteristic (FROC). Finally, the CNN-inferred maximum diameter was compared against expert measurements by Pearson's correlation and Bland-Altman limits of agreement (LOA). A total of 451 patients with 3D-RA images were split into n = 347/41/63 training/validation/test datasets, respectively. For aneurysm detection, observed FROC analysis showed that the model managed to attain a sensitivity of 0.710 at 0.159 false positives (FP)/case, and 0.986 at 1.49 FP/case. The proposed method had good agreement with reference manual aneurysmal maximum diameter measurements (8.3 ± 4.3 mm vs. 7.8 ± 4.8 mm), with a correlation coefficient r = 0.77, small bias of 0.24 mm, and LOA of -6.2 to 5.71 mm. 37.0% and 77% of diameter measurements were within ±1 mm and ±2.5 mm of expert measurements. A 3D-Dense-UNet model can detect and segment aneurysms with relatively high accuracy using 3D-RA images. The automatically measured maximum diameter has potential clinical application value.

Deep Learning for Detection of Intracranial Aneurysms From Computed Tomography Angiography Images

Background: The rates of the fatality and disability will be extremely high once the intracranial aneurysms rupture. Radiologic examination based on the computed tomography angiography (CTA) images is the preferred method for the diagnosis of intracranial aneurysms, where the interpretation of imaging data is usually performed by an experienced radiologist. However, the accuracy of the interpretation and the time spent highly rely on the professional competence of the radiologist, which may yield inconsistent diagnostic outcomes. In addition, with steadily increasing workloads of radiology departments for providing various imaging diagnostic services, the fatigue of radiologists due to overloading may cause them neglecting or mistaking interpretations. Therefore, the aim of this study was to develop a new method to automatically detect intracranial aneurysms from CTA images using deep learning based on convolutional neural network (CNN) implemented on the Deepmedic platform. This new method can serve as a clinical diagnostic tool or a preliminary reference for diagnosis of intracranial aneurysms. It will be of great clinical value in reducing the diagnosis time and the missed or mistaken diagnosis caused by radiologists' different professional levels or their fatigue. Methods: We implemented a deep learning architecture with a 3D CNN model on Deepmedic platform for automatic segmentation and detection of intracranial aneurysms from CTA images which were retrospectively collected. The retrospective dataset was preprocessed and then was divided into two parts: the training part (80 subjects) to train the CNN model, and the testing part (10 subjects) to evaluate the performance of the automatic detection system. Sensitivity, positive predictive value (PPV) and the false positives per case were evaluated with the reference standard of digital subtraction angiography (DSA) or intraoperative results. Findings: The overall sensitivity and PPV of this system for the detection of intracranial aneurysms from CTA images were 92.3% and 100%, and the segmentation sensitivity also was 92.3%. The performance of the system in the detection of intracranial aneurysms was related to their size: the detection sensitivity for tiny intracranial aneurysms with a diameter ≤ 3mm was 66.7%, whereas the sensitivities of detection for large and medium-sized intracranial aneurysms of > 3mm both were 100%. Interpretation: The deep learning architecture with a 3D CNN model on Deepmedic platform could reliably segment and detect intracranial aneurysms from CTA images with an extremely high sensitivity, especially for large and medium-sized intracranial aneurysms, and this required only very limited training samples. Moreover, the detection sensitivity of tiny intracranial aneurysms was higher than those reported recently in other studies. Funding Statement: This study was supported in part by National Natural Science Foundation of China (81601558), Breeding Foundation of Zhuhai People's Hospital of China (2019PY-16) and Medical Research Foundation of Zhuhai City of China (20191207A010017). Declaration of Interests: No authors report any financial relationships with commercial interests Ethics Approval Statement: This retrospective study was approved by the Ethics Committee of Zhuhai People’s Hospital and the First Affiliated Hospital of Harbin Medical University.

Fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning

In aneurysmal subarachnoid hemorrhage (aSAH), accurate diagnosis of aneurysm is essential for subsequent treatment to prevent rebleeding. However, aneurysm detection proves to be challenging and time-consuming. The purpose of this study was to develop and evaluate a deep learning model (DLM) to automatically detect and segment aneurysms in patients with aSAH on computed tomography angiography. In this retrospective single-center study, three different DLMs were trained on 68 patients with 79 aneurysms treated for aSAH (2016–2017) using five-fold-cross-validation. Their outputs were combined to a single DLM via ensemble-learning. The DLM was evaluated on an independent test set consisting of 185 patients with 215 aneurysms (2010–2015). Independent manual segmentations of aneurysms in a 3D voxel-wise manner by two readers (neurosurgeon, radiologist) provided the reference standard. For aneurysms > 30 mm3 (mean diameter of ~ 4 mm) on the test set, the DLM provided a detection sensitivity of 87% with false positives (FPs)/scan of 0.42. Automatic segmentations achieved a median dice similarity coefficient (DSC) of 0.80 compared to the reference standard. Aneurysm location (anterior vs. posterior circulation; P = .07) and bleeding severity (Fisher grade ≤ 3 vs. 4; P = .33) did not impede detection sensitivity or segmentation performance. For aneurysms > 100 mm3 (mean diameter of ~ 6 mm), a sensitivity of 96% with DSC of 0.87 and FPs/scan of 0.14 were obtained. In the present study, we demonstrate that the proposed DLM detects and segments aneurysms > 30 mm3 in patients with aSAH with high sensitivity independent of cerebral circulation and bleeding severity while producing FP findings of less than one per scan. Hence, the DLM can potentially assist treating physicians in aSAH by providing automated detection and segmentations of aneurysms.

1D CNN-Based Intracranial Aneurysms Detection in 3D TOF-MRA

How to automatically detect intracranial aneurysms from Three-Dimension Time of Flight Magnetic Resonance Angiography (3D TOF MRA) images is a typical 3D image classification problem. Currently, the commonly used method is the Maximum Intensity Projection- (MIP-) based way. It transfers 3D classification into 2D case by projecting the 3D patch into 2D planes along different directions on the basis of voxel’s intensity. After then, the 2D Convolutional Neural Network (CNN) is established to do classification. It has been shown that the MIP-based method can reduce the demands for the samples and increase the computation efficiency. Meanwhile, the accuracy is comparable with that of 3D image classification. Inspired by the strategy of MIP, we want to further reduce the demands for samples and accelerate the training by transferring the 2D image classification into 1D case, i.e., we want to generate the 1D vectors from the MIP images and then establish a 1D CNN to do intracranial aneurysm detection and classification for 3D TOF MRA image. Specifically, our method first extracts a series of patches as the Region of Interests (ROIs) along the blood vessels from the original 3D TOF MRA 3D image. The corresponding MIP images of each ROI will be obtained through maximum intensity projecting. Then, we generate a series of 1D vectors by accumulating each MIP image along different directions. Meanwhile, a 1D CNN is established to detect aneurysms, in which, the input is the obtained 1D vectors and the output is the binary classification result denoting whether there are intracranial aneurysms in the considered patch. Generally, compared with 2D- and 3D-CNN, the 1D CNN-based way greatly accelerates the training and shows stronger robustness in the case of fewer samples. The efficiency of the proposed method outperforms the 2D CNN about 10 times in CPU training. Yet, their accuracies are close.

Intracranial aneurysm and coarctation of the aorta: prevalence in the current era.

A 10% prevalence of intracranial aneurysms in patients with coarctation of the aorta has been described in a few studies. Our objective is to describe the rate of intracranial aneurysm detection in patients with coarctation of the aorta in the current era. We hypothesise that, with earlier detection and coarctation of the aorta intervention, the rate of intracranial aneurysm is lower than previously reported and screening imaging may only be warranted in older patients or patients with certain risk factors. This is a retrospective study of 102 patients aged 13 years and older with coarctation who underwent brain computed tomography angiography, magnetic resonance imaging (MRI), or magnetic resonance angiography between January, 2000 and February, 2018. The median age of coarctation repair was 4.4 months (2 days-47 years) and the initial repair was primarily surgical (90.2%). There were 11 former smokers, 4 current smokers, and 13 patients with ongoing hypertension. Imaging modalities included computed tomography angiography (13.7%), MRI (41.2%), and magnetic resonance angiography (46.1%), performed at a median age of 33.3 years, 22.4 years, and 25 years, respectively. There were 42 studies performed for screening, 48 studies performed for neurologic symptoms, and 12 studies performed for both screening and symptoms. There were no intracranial aneurysms detected in this study. These results suggest that the rate of intracranial aneurysms may be lower than previously reported and larger studies should explore the risk of intracranial aneurysms in coarctation of the aorta in the current era.

Automatic detection of intracranial aneurysms in 3D-DSA based on a Bayesian optimized filter

BackgroundIntracranial aneurysm is a common type of cerebrovascular disease with a risk of devastating subarachnoid hemorrhage if it is ruptured. Accurate computer-aided detection of aneurysms can help doctors improve the diagnostic accuracy, and it is very helpful in reducing the risk of subarachnoid hemorrhage. Aneurysms are detected in 2D or 3D images from different modalities. 3D images can provide more vascular information than 2D images, and it is more difficult to detect. The detection performance of 2D images is related to the angle of view; it may take several angles to determine the aneurysm. As the gold standard for the diagnosis of vascular diseases, the detection on digital subtraction angiography (DSA) has more clinical value than other modalities. In this study, we proposed an adaptive multiscale filter to detect intracranial aneurysms on 3D-DSA.MethodsAdaptive aneurysm detection consists of three parts. The first part is a filter based on Hessian matrix eigenvalues, whose parameters are automatically obtained by Bayesian optimization. The second part is aneurysm extraction based on region growth and adaptive thresholding. The third part is the iterative detection strategy for multiple aneurysms.ResultsThe proposed method was quantitatively evaluated on data sets of 145 patients. The results showed a detection precision of 94.6%, and a sensitivity of 96.4% with a false-positive rate of 6.2%. Among aneurysms smaller than 5 mm, 93.9% were found. Compared with aneurysm detection on 2D-DSA, automatic detection on 3D-DSA can effectively reduce the misdiagnosis rate and obtain more accurate detection results. Compared with other modalities detection, we also get similar or better detection performance.ConclusionsThe experimental results show that the proposed method is stable and reliable for aneurysm detection, which provides an option for doctors to accurately diagnose aneurysms.