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

A survey of intracranial aneurysm detection and segmentation

Intracranial aneurysms (IAs) are a critical public health concern: they are asymptomatic and can lead to fatal subarachnoid hemorrhage in case of rupture. Neuroradiologists rely on advanced imaging techniques to identify aneurysms in a patient and consider the characteristics of IAs along with several other patient-related factors for rupture risk assessment and treatment decision-making. The process of diagnostic image reading is time-intensive and prone to inter- and intra-individual variations, so researchers have proposed many computer-aided diagnosis (CAD) systems for aneurysm detection and segmentation. This paper provides a comprehensive literature survey of semi-automated and automated approaches for IA detection and segmentation and proposes a taxonomy to classify the approaches. We also discuss the current issues and give some insight into the future direction of CAD systems for IA detection and segmentation.

Deep learning-based cerebral aneurysm segmentation and morphological analysis with three-dimensional rotational angiography

BACKGROUND

The morphological assessment of cerebral aneurysms based on cerebral angiography is an essential step when planning strategy and device selection in endovascular treatment, but manual evaluation by human raters only has moderate interrater/intrarater reliability.

METHODS

We collected data for 889 cerebral angiograms from consecutive patients with suspected cerebral aneurysms at our institution from January 2017 to October 2021. The automatic morphological analysis model was developed on the derivation cohort dataset consisting of 388 scans with 437 aneurysms, and the performance of the model was tested on the validation cohort dataset consisting of 96 scans with 124 aneurysms. Five clinically important parameters were automatically calculated by the model: aneurysm volume, maximum aneurysm size, neck size, aneurysm height, and aspect ratio.

RESULTS

On the validation cohort dataset the average aneurysm size was 7.9±4.6 mm. The proposed model displayed high segmentation accuracy with a mean Dice similarity index of 0.87 (median 0.93). All the morphological parameters were significantly correlated with the reference standard (all P<0.0001; Pearson correlation analysis). The difference in the maximum aneurysm size between the model prediction and reference standard was 0.5±0.7 mm (mean±SD). The difference in neck size between the model prediction and reference standard was 0.8±1.7 mm (mean±SD).

CONCLUSION

The automatic aneurysm analysis model based on angiography data exhibited high accuracy for evaluating the morphological characteristics of cerebral aneurysms.

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

INTRODUCTION

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.

METHODS

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.

RESULTS

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.

CONCLUSION

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.

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

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

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

BACKGROUND

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

METHODS

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

PROSPERO

CRD42021278454.

RESULTS

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

CONCLUSION

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

Towards Automated Brain Aneurysm Detection in TOF-MRA: Open Data, Weak Labels, and Anatomical Knowledge

Brain aneurysm detection in Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) has undergone drastic improvements with the advent of Deep Learning (DL). However, performances of supervised DL models heavily rely on the quantity of labeled samples, which are extremely costly to obtain. Here, we present a DL model for aneurysm detection that overcomes the issue with "weak" labels: oversized annotations which are considerably faster to create. Our weak labels resulted to be four times faster to generate than their voxel-wise counterparts. In addition, our model leverages prior anatomical knowledge by focusing only on plausible locations for aneurysm occurrence. We first train and evaluate our model through cross-validation on an in-house TOF-MRA dataset comprising 284 subjects (170 females / 127 healthy controls / 157 patients with 198 aneurysms). On this dataset, our best model achieved a sensitivity of 83%, with False Positive (FP) rate of 0.8 per patient. To assess model generalizability, we then participated in a challenge for aneurysm detection with TOF-MRA data (93 patients, 20 controls, 125 aneurysms). On the public challenge, sensitivity was 68% (FP rate = 2.5), ranking 4th/18 on the open leaderboard. We found no significant difference in sensitivity between aneurysm risk-of-rupture groups (p = 0.75), locations (p = 0.72), or sizes (p = 0.15). Data, code and model weights are released under permissive licenses. We demonstrate that weak labels and anatomical knowledge can alleviate the necessity for prohibitively expensive voxel-wise annotations.

A deep learning-based automatic system for intracranial aneurysms diagnosis on three-dimensional digital subtraction angiographic images

BACKGROUND

Intracranial aneurysms (IAs) are a life-threatening disease. Their rupture can lead to hemorrhagic stroke. Most studies applying deep learning for the detection of aneurysms are based on angiographic images. However, critical diagnostic information such as morphology and aneurysm location are not captured by deep learning algorithms and still require manual assessments.

PURPOSE

Digital subtraction angiography (DSA) is the gold standard for aneurysm diagnosis. To facilitate the fully automatic diagnosis of aneurysms, we proposed a comprehensive system for the detection, morphology measurement, and location classification of aneurysms on three-dimensional DSA images, allowing automatic diagnosis without further human input.

METHODS

The system comprised three neural networks: a network for aneurysm detection, a network for morphology measurement, and a network for aneurysm location identification. A cross-scale dual-path transformer module was proposed to effectively fuse local and global information to capture aneurysms of varying sizes. A multitask learning approach was also proposed to allow an accurate localization of aneurysm neck for morphology measurement.

RESULTS

The cross-scale dual-path transformer module was shown to outperform other state-of-the-art network architectures, improving segmentation, and classification accuracy. The detection network in our system achieved an F2 score of 0.946 (recall 93%, precision 100%), better than the winning team in the Cerebral Aneurysm Detection and Analysis challenge. The measurement network achieved a relative error of less than 10% for morphology measurement, at the same level as human operators. Perfect accuracy (100%) was achieved on aneurysm location classification.

CONCLUSIONS

We have demonstrated that a comprehensive system can automatically detect, measure morphology and report the aneurysm location of aneurysms without human intervention. This can be a potential tool for the diagnosis of IAs, improving radiologists' performance and reducing their workload.

A Novel Method for Improving the Accuracy of MR-derived Patient-specific Vascular Models using X-ray Angiography

MR imaging, a noninvasive radiation-free imaging modality commonly used during clinical follow up, has been widely utilized to reconstruct realistic 3D vascular models for patient-specific analysis. In recent work, we used patient-specific hemodynamic analysis of the circle of Willis to noninvasively assess stroke risk in pediatric Moyamoya disease (MMD)-a progressive steno-occlusive cerebrovascular disorder that leads to recurrent stroke. The objective was to identify vascular regions with critically high wall shear rate (WSR) that signifies elevated stroke risk. However, sources of error such as insufficient resolution of MR images can negatively impact vascular model accuracy, especially in areas of severe pathological narrowing, and thus diminish clinical relevance of simulation results, as local hemodynamics are sensitive to vessel geometry. To improve the accuracy of MR-derived vascular models, we have developed a novel method for adjusting model vessel geometry utilizing 2D X-ray angiography (XA), which is considered the gold standard for clinically assessing vessel caliber. In this workflow, "virtual angiographies" (VAs) of 3D MR-derived vascular models are conducted, producing 2D projections that are compared with corresponding XA images to guide the local adjustment of modeled vessels. This VA-comparison-adjustment loop is iterated until the two agree, as confirmed by an expert neuroradiologist. Using this method, we generated models of the circle of Willis of two patients with a history of unilateral stroke. Blood flow simulations were performed using a Navier-Stokes solver within an isogeometric analysis framework, and WSR distributions were quantified. Results for one patient show as much as 45% underestimation of local WSR in the stenotic left anterior cerebral artery (LACA), and up to a 56% underestimation in the right anterior cerebral artery when using the initial MR-derived model compared to the XA-adjusted model. To evaluate whether XA-based adjustment improves model accuracy, vessel cross-sectional areas of the pre- and post-adjustment models were compared to those seen in 3D CTA images of the same patient. CTA has superior resolution and signal-to-noise ratio compared to MR imaging but is not commonly used in the clinic due to radiation exposure concerns, especially in pediatric patients. While the vessels in the initial model had normalized root mean squared deviations (NRMSDs) ranging from 26% to 182% and 31% to 69% in two patients with respect to CTA, the adjusted vessel NRMSDs were comparatively smaller (32% to 53% and 11% to 42%). In the mildly stenotic LACA of patient 1, the NRMSDs for the pre- and post-adjusted models were 49% and 32%, respectively. These findings suggest that our XA-based adjustment method can considerably improve the accuracy of vascular models, and thus, stroke-risk prediction. An accurate, individualized assessment of stroke risk would be of substantial help in guiding the timing of preventive surgical interventions in pediatric MMD patients.

Development of an Artificial Neural Network for the Detection of Supporting Hindlimb Lameness: A Pilot Study in Working Dogs

Subjective lameness assessment has been a controversial subject given the lack of agreement between observers; this has prompted the development of kinetic and kinematic devices in order to obtain an objective evaluation of locomotor system in dogs. After proper training, neural networks are potentially capable of making a non-human diagnosis of canine lameness. The purpose of this study was to investigate whether artificial neural networks could be used to determine canine hindlimb lameness by computational means only. The outcome of this study could potentially assess the efficacy of certain treatments against diseases that cause lameness. With this aim, input data were obtained from an inertial sensor positioned on the rump. Data from dogs with unilateral hindlimb lameness and sound dogs were used to obtain differences between both groups at walk. The artificial neural network, after necessary adjustments, was integrated into a web management tool, and the preliminary results discriminating between lame and sound dogs are promising. The analysis of spatial data with artificial neural networks was summarized and developed into a web app that has proven to be a useful tool to discriminate between sound and lame dogs. Additionally, this environment allows veterinary clinicians to adequately follow the treatment of lame canine patients.

Robotics and Artificial Intelligence in Endovascular Neurosurgery

The use of artificial intelligence (AI) and robotics in endovascular neurosurgery promises to transform neurovascular care. We present a review of the recently published neurosurgical literature on artificial intelligence and robotics in endovascular neurosurgery to provide insights into the current advances and applications of this technology.

The PubMed database was searched for "neurosurgery" OR "endovascular" OR "interventional" AND "robotics" OR "artificial intelligence" between January 2016 and August 2021. A total of 1296 articles were identified, and after applying the inclusion and exclusion criteria, 38 manuscripts were selected for review and analysis. These manuscripts were divided into four categories: 1) robotics and AI for the diagnosis of cerebrovascular pathology, 2) robotics and AI for the treatment of cerebrovascular pathology, 3) robotics and AI for training in neuroendovascular procedures, and 4) robotics and AI for clinical outcome optimization.

The 38 articles presented include 23 articles on AI-based diagnosis of cerebrovascular disease, 10 articles on AI-based treatment of cerebrovascular disease, two articles on AI-based training techniques for neuroendovascular procedures, and three articles reporting AI prediction models of clinical outcomes in vascular disorders of the brain. Innovation with robotics and AI focus on diagnostic efficiency, optimizing treatment and interventional procedures, improving physician procedural performance, and predicting clinical outcomes with the use of artificial intelligence and robotics. Experimental studies with robotic systems have demonstrated safety and efficacy in treating cerebrovascular disorders, and novel microcatheterization techniques may permit access to deeper brain regions. Other studies show that pre-procedural simulations increase overall physician performance. Artificial intelligence also shows superiority over existing statistical tools in predicting clinical outcomes.

The recent advances and current usage of robotics and AI in the endovascular neurosurgery field suggest that the collaboration between physicians and machines has a bright future for the improvement of patient care. The aim of this work is to equip the medical readership, in particular the neurosurgical specialty, with tools to better understand and apply findings from research on artificial intelligence and robotics in endovascular neurosurgery.