Machine Learning Application for Rupture Risk Assessment in Small-Sized Intracranial Aneurysm

Intracranial aneurysm CTA images and 3D models dataset with clinical morphological and hemodynamic data

Intracranial aneurysm is a cerebrovascular disease associated with a high rupture risk, often resulting in death or severe disability. Recent advances in AI enable the prediction of intracranial aneurysm initiation, progression, and rupture through medical image analysis. Despite growing research interest, there is a shortage of publicly available datasets for training and validating AI models. This paper presents a comprehensive dataset comprising high-resolution CTA images of 99 patients with 105 MCA aneurysms and 44 normal healthy controls, along with their respective clinical data and 3D models of aneurysms and the parent arteries derived from the CTA images. Furthermore, recognizing the significance of blood hemodynamics on aneurysm development, this dataset also included the morphological and hemodynamic parameters obtained by computational fluid dynamics (CFD) for each patient and healthy control, which can be utilized by researchers without prior CFD experience. This dataset will facilitate hypothesis-driven or data-driven research on intracranial aneurysms, and has the potential to deepen our understanding of this disease.

Artificial intelligence applied to development of predictive stability model for intracranial aneurysms

BACKGROUND

We aimed to develop multiple machine learning models to predict the risk of early intracranial aneurysms (IAs) rupture, evaluate and compare the performance of predictive models.

METHODS

Information related to patients diagnosed with IA by CT angiography and clinicians in Central hospital of Dalian University of Technology from January 2010 to June 2022 was collected, including clinical characteristics, blood indicators and IA morphological parameters. IA with rupture or maximum growth ≥ 0.5 mm within 1 month of first diagnosis was considered unstable. The relevant factors affecting IA stability were screened and predictive models were developed based on the above three levels, including random forest (RF), support vector machine (SVM), and artificial neural network (ANN). Sensitivity, specificity, accuracy and area under curve (AUC) value were used to evaluate the predictive models.

RESULTS

A total of 989 IA patients were included in the study, including 561 stable patients and 428 unstable patients. For RF models, the training set showed that sensitivity, specificity, accuracy and the AUC values were 72.8-83.7%, 76.9-86.9%, 75.1-84.1% and 0.748 (0.719-0.778)-0.839 (0.814-0.864), respectively; after test set validation, the results were 71.9-78.8%, 75.0-84.0%, 73.6-81.1% and 0.734 (0.688-0.781)-0.809 (0.768-0.850), respectively. For SVM models, the training set were 66.0-80.2%, 76.5-85.5%, 71.7-82.3%, 0.712 (0.682-0.743)-0.913 (0.884-0.924), respectively; the test set were 44.2-78.3%, 63.4-84.4%, 57.9-80.9%, 0.699 (0.651-0.747)-0.806 (0.765-0.848), respectively. For ANN models, the training set were 66.8-83.0%, 75.3-82.3%, 71.6-82.1%, 0.783 (0.757-0.808)-0.897 (0.879-0.914); the test set were 63.1-76.3%, 65.5-84.0%, 64.4-80.6%, 0.680 (0.593-0.694)-0.860 (0.821-0.899). The results of variable importance showed that age, white blood cell count (WBC) and uric acid (UA) played an important role in predicting the stability of IA.

CONCLUSIONS

The predictive stability models of IA based on three artificial intelligence methods shows good clinical application. Age, WBC and UA played an important role in predicting the IA stability, and were potentially important predictors.

Risk factors and predictive indicators of rupture in cerebral aneurysms

Cerebral aneurysms are abnormal dilations of blood vessels in the brain that have the potential to rupture, leading to subarachnoid hemorrhage and other serious complications. Early detection and prediction of aneurysm rupture are crucial for effective management and prevention of rupture-related morbidities and mortalities. This review aims to summarize the current knowledge on risk factors and predictive indicators of rupture in cerebral aneurysms. Morphological characteristics such as aneurysm size, shape, and location, as well as hemodynamic factors including blood flow patterns and wall shear stress, have been identified as important factors influencing aneurysm stability and rupture risk. In addition to these traditional factors, emerging evidence suggests that biological and genetic factors, such as inflammation, extracellular matrix remodeling, and genetic polymorphisms, may also play significant roles in aneurysm rupture. Furthermore, advancements in computational fluid dynamics and machine learning algorithms have enabled the development of novel predictive models for rupture risk assessment. However, challenges remain in accurately predicting aneurysm rupture, and further research is needed to validate these predictors and integrate them into clinical practice. By elucidating and identifying the various risk factors and predictive indicators associated with aneurysm rupture, we can enhance personalized risk assessment and optimize treatment strategies for patients with cerebral aneurysms.

Integrating PointNet-Based Model and Machine Learning Algorithms for Classification of Rupture Status of IAs

BACKGROUND

The rupture of intracranial aneurysms (IAs) would result in subarachnoid hemorrhage with high mortality and disability. Predicting the risk of IAs rupture remains a challenge.

METHODS

This paper proposed an effective method for classifying IAs rupture status by integrating a PointNet-based model and machine learning algorithms. First, medical image segmentation and reconstruction algorithms were applied to 3D Digital Subtraction Angiography (DSA) imaging data to construct three-dimensional IAs geometric models. Geometrical parameters of IAs were then acquired using Geomagic, followed by the computation of hemodynamic clouds and hemodynamic parameters using Computational Fluid Dynamics (CFD). A PointNet-based model was developed to extract different dimensional hemodynamic cloud features. Finally, five types of machine learning algorithms were applied on geometrical parameters, hemodynamic parameters, and hemodynamic cloud features to classify and recognize IAs rupture status. The classification performance of different dimensional hemodynamic cloud features was also compared.

RESULTS

The 16-, 32-, 64-, and 1024-dimensional hemodynamic cloud features were extracted with the PointNet-based model, respectively, and the four types of cloud features in combination with the geometrical parameters and hemodynamic parameters were respectively applied to classify the rupture status of IAs. The best classification outcomes were achieved in the case of 16-dimensional hemodynamic cloud features, the accuracy of XGBoost, CatBoost, SVM, LightGBM, and LR algorithms was 0.887, 0.857, 0.854, 0.857, and 0.908, respectively, and the AUCs were 0.917, 0.934, 0.946, 0.920, and 0.944. In contrast, when only utilizing geometrical parameters and hemodynamic parameters, the accuracies were 0.836, 0.816, 0.826, 0.832, and 0.885, respectively, with AUC values of 0.908, 0.922, 0.930, 0.884, and 0.921.

CONCLUSION

In this paper, classification models for IAs rupture status were constructed by integrating a PointNet-based model and machine learning algorithms. Experiments demonstrated that hemodynamic cloud features had a certain contribution weight to the classification of IAs rupture status. When 16-dimensional hemodynamic cloud features were added to the morphological and hemodynamic features, the models achieved the highest classification accuracies and AUCs. Our models and algorithms would provide valuable insights for the clinical diagnosis and treatment of IAs.

Imaging of Intracranial Aneurysms: A Review of Standard and Advanced Imaging Techniques

The treatment of intracranial aneurysms is dictated by its risk of rupture in the future. Several clinical and radiological risk factors for aneurysm rupture have been described and incorporated into prediction models. Despite the recent technological advancements in aneurysm imaging, linear length and visible irregularity with a bleb are the only radiological measure used in clinical prediction models. The purpose of this article is to summarize both the standard imaging techniques, including their limitations, and the advanced techniques being used experimentally to image aneurysms. It is expected that as our understanding of advanced techniques improves, and their ability to predict clinical events is demonstrated, they become an increasingly routine part of aneurysm assessment. It is important that neurovascular specialists understand the spectrum of imaging techniques available.

Compare deep learning model and conventional logistic regression model for the identification of unstable saccular intracranial aneurysms in computed tomography angiography

Background

It is crucial to distinguish unstable from stable intracranial aneurysms (IAs) as early as possible to derive optimal clinical decision-making for further treatment or follow-up. The aim of this study was to investigate the value of a deep learning model (DLM) in identifying unstable IAs from computed tomography angiography (CTA) images and to compare its discriminatory ability with that of a conventional logistic regression model (LRM).

Methods

From August 2011 to May 2021, a total of 1,049 patients with 681 unstable IAs and 556 stable IAs were retrospectively analyzed. IAs were randomly divided into training (64%), internal validation (16%), and test sets (20%). Convolutional neural network (CNN) analysis and conventional logistic regression (LR) were used to predict which IAs were unstable. The area under the curve (AUC), sensitivity, specificity and accuracy were calculated to evaluate the discriminating ability of the models. One hundred and ninety-seven patients with 229 IAs from Banan Hospital were used for external validation sets.

Results

The conventional LRM showed 11 unstable risk factors, including clinical and IA characteristics. The LRM had an AUC of 0.963 [95% confidence interval (CI): 0.941-0.986], a sensitivity, specificity and accuracy on the external validation set of 0.922, 0.906, and 0.913, respectively, in predicting unstable IAs. In predicting unstable IAs, the DLM had an AUC of 0.771 (95% CI: 0.582-0.960), a sensitivity, specificity and accuracy on the external validation set of 0.694, 0.929, and 0.782, respectively.

Conclusions

The CNN-based DLM applied to CTA images did not outperform the conventional LRM in predicting unstable IAs. The patient clinical and IA morphological parameters remain critical factors for ensuring IA stability. Further studies are needed to enhance the diagnostic accuracy.

Assessment of intracranial aneurysm rupture risk using a point cloud-based deep learning model

Background and Purpose: Precisely assessing the likelihood of an intracranial aneurysm rupturing is critical for guiding clinical decision-making. The objective of this study is to construct and validate a deep learning framework utilizing point clouds to forecast the likelihood of aneurysm rupturing. Methods: The dataset included in this study consisted of a total of 623 aneurysms, with 211 of them classified as ruptured and 412 as unruptured, which were obtained from two separate projects within the AneuX morphology database. The HUG project, which included 124 ruptured aneurysms and 340 unruptured aneurysms, was used to train and internally validate the model. For external validation, another project named @neurIST was used, which included 87 ruptured and 72 unruptured aneurysms. A standardized method was employed to isolate aneurysms and a segment of their parent vessels from the original 3D vessel models. These models were then converted into a point cloud format using open3d package to facilitate training of the deep learning network. The PointNet++ architecture was utilized to process the models and generate risk scores through a softmax layer. Finally, two models, the dome and cut1 model, were established and then subjected to a comprehensive comparison of statistical indices with the LASSO regression model built by the dataset authors. Results: The cut1 model outperformed the dome model in the 5-fold cross-validation, with the mean AUC values of 0.85 and 0.81, respectively. Furthermore, the cut1 model beat the morphology-based LASSO regression model with an AUC of 0.82. However, as the original dataset authors stated, we observed potential generalizability concerns when applying trained models to datasets with different selection biases. Nevertheless, our method outperformed the LASSO regression model in terms of generalizability, with an AUC of 0.71 versus 0.67. Conclusion: The point cloud, as a 3D visualization technique for intracranial aneurysms, can effectively capture the spatial contour and morphological aspects of aneurysms. More structural features between the aneurysm and its parent vessels can be exposed by keeping a portion of the parent vessels, enhancing the model's performance. The point cloud-based deep learning model exhibited good performance in predicting rupture risk while also facing challenges in generalizability.

Prediction of cerebral aneurysm rupture risk by machine learning algorithms: a systematic review and meta-analysis of 18,670 participants

It is possible to identify unruptured intracranial aneurysms (UIA) using machine learning (ML) algorithms, which can be a life-saving strategy, especially in high-risk populations. To better understand the importance and effectiveness of ML algorithms in practice, a systematic review and meta-analysis were conducted to predict cerebral aneurysm rupture risk. PubMed, Scopus, Web of Science, and Embase were searched without restrictions until March 20, 2023. Eligibility criteria included studies that used ML approaches in patients with cerebral aneurysms confirmed by DSA, CTA, or MRI. Out of 35 studies included, 33 were cohort, and 11 used digital subtraction angiography (DSA) as their reference imaging modality. Middle cerebral artery (MCA) and anterior cerebral artery (ACA) were the commonest locations of aneurysmal vascular involvement-51% and 40%, respectively. The aneurysm morphology was saccular in 48% of studies. Ten of 37 studies (27%) used deep learning techniques such as CNNs and ANNs. Meta-analysis was performed on 17 studies: sensitivity of 0.83 (95% confidence interval (CI), 0.77-0.88); specificity of 0.83 (95% CI, 0.75-0.88); positive DLR of 4.81 (95% CI, 3.29-7.02) and the negative DLR of 0.20 (95% CI, 0.14-0.29); a diagnostic score of 3.17 (95% CI, 2.55-3.78); odds ratio of 23.69 (95% CI, 12.75-44.01). ML algorithms can effectively predict the risk of rupture in cerebral aneurysms with good levels of accuracy, sensitivity, and specificity. However, further research is needed to enhance their diagnostic performance in predicting the rupture status of IA.

Global trend in research of intracranial aneurysm management with artificial intelligence technology: a bibliometric analysis

Background

The use of artificial intelligence (AI) technology has been growing in the management of intracranial aneurysms (IAs). This study aims to conduct a bibliometric analysis of researches on intracranial aneurysm management with artificial intelligence technology (IAMWAIT) to gain insights into global research trends and potential future directions.

Methods

A comprehensive search of articles and reviews related to IAMWAIT, published from January 1, 1900 to July 20, 2023, was conducted using the Web of Science Core Collection (WoWCC).Visualizations of the bibliometric analysis were generated utilizing WPS Office, Scimago Graphica, VOSviewer, CiteSpace, and R.

Results

A total of 277 papers were included in the study. China emerged as the most prolific country in terms of publications, institutions, cooperating countries, and prolific authors. The United States garnered the highest number of total citations, institutions with the highest citations/H index, cooperating countries (n=9), and 3 of the top 10 cited papers. Both the total number of papers and the citation count exhibited a positive and significant correlation with the gross domestic product (GDP) of countries. The journal with the highest publication frequency was Frontiers in Neurology, while Stroke recorded the highest number of citations, H-index, and impact factor (IF). Areas of primary interest in IAMWAIT, leveraging AI technology, included rupture risk assessment/prediction, computer-assisted diagnosis, outcome prediction, hemodynamics, and laboratory research of IAs.

Conclusions

IAMWAIT is an active area of research that has undergone rapid development in recent years. Future endeavors should focus on broader application of AI algorithms in various sub-fields of IAMWAIT to better suit the real world.

Artificial intelligence and machine learning in aneurysmal subarachnoid hemorrhage: Future promises, perils, and practicalities

INTRODUCTION

Aneurysmal subarachnoid hemorrhage (SAH) is a subtype of hemorrhagic stroke with thirty-day mortality as high as 40%. Given the expansion of Machine Learning (ML) and Artificial intelligence (AI) methods in health care, SAH patients desperately need an integrated AI system that detects, segments, and supports clinical decisions based on presentation and severity.

OBJECTIVES

This review aims to synthesize the current state of the art of AI and ML tools for the management of SAH patients alongside providing an up-to-date account of future horizons in patient care.

METHODS

We performed a systematic review through various databases such as Cochrane Central Register of Controlled Trials, MEDLINE, Scopus, Cochrane Database of Systematic Reviews, and Embase.

RESULTS

A total of 507 articles were identified. Following extensive revision, only 21 articles were relevant. Two studies reported improved mortality prediction using Glasgow Coma Scale and biomarkers such as Neutrophil to Lymphocyte Ratio and glucose. One study reported that ffANN is equal to the SAHIT and VASOGRADE scores. One study reported that metabolic biomarkers Ornithine, Symmetric Dimethylarginine, and Dimethylguanidine Valeric acid were associated with poor outcomes. Nine studies reported improved prediction of complications and reduction in latency until intervention using clinical scores and imaging. Four studies reported accurate prediction of aneurysmal rupture based on size, shape, and CNN. One study reported AI-assisted Robotic Transcranial Doppler as a substitute for clinicians.

CONCLUSION

AI/ML technologies possess tremendous potential in accelerating SAH systems-of-care. Keeping abreast of developments is vital in advancing timely interventions for critical diseases.

A systematic review on intracranial aneurysm and hemorrhage detection using machine learning and deep learning techniques

The risk of discovering an intracranial aneurysm during the initial screening and follow-up screening are reported as around 11%, and 7% respectively (Zuurbie et al., 2023) to these mass effects, unruptured aneurysms frequently generate symptoms, however, the real hazard occurs when an aneurysm ruptures and results in a cerebral hemorrhage known as a subarachnoid hemorrhage. The objective is to study the multiple kinds of hemorrhage and aneurysm detection problems and develop machine and deep learning models to recognise them. Due to its early stage, subarachnoid hemorrhage, the most typical symptom after aneurysm rupture, is an important medical condition. It frequently results in severe neurological emergencies or even death. Although most aneurysms are asymptomatic and won't burst, because of their unpredictable growth, even small aneurysms are susceptible. A timely diagnosis is essential to prevent early mortality because a large percentage of hemorrhage cases present can be fatal. Physiological/imaging markers and the degree of the subarachnoid hemorrhage can be used as indicators for potential early treatments in hemorrhage. The hemodynamic pathomechanisms and microcellular environment should remain a priority for academics and medical professionals. There is still disagreement about how and when to care for aneurysms that have not ruptured despite studies reporting on the risk of rupture and outcomes. We are optimistic that with the progress in our understanding of the pathophysiology of hemorrhages and aneurysms and the advancement of artificial intelligence has made it feasible to conduct analyses with a high degree of precision, effectiveness and reliability.

Development of Cloud-Based Telemedicine Platform for Acute Intracerebral Hemorrhage in Gangwon-do : Concept and Protocol

We aimed to develop a cloud-based telemedicine platform for patients with intracerebral hemorrhage (ICH) at local hospitals in rural and underserved areas in Gangwon-do using artificial intelligence and non-face-to-face collaboration treatment technology. This is a prospective and multi-center development project in which neurosurgeons from four university hospitals in Gangwondo will participate. Information technology experts will verify and improve the performance of the cloud-based telemedicine collaboration platform while treating ICH patients in the actual medical field. Problems identified will be resolved, and the function, performance, security, and safety of the telemedicine platform will be checked through an accredited certification authority. The project will be carried out over 4 years and consists of two phases. The first phase will be from April 2022 to December 2023, and the second phase will be from April 2024 to December 2025. The platform will be developed by dividing the work of the neurosurgeons and information technology experts by setting the order of items through mutual feedback. This article provides information on a project to develop a cloud-based telemedicine platform for acute ICH patients in Gangwon-do.

SAD score of intracranial aneurysms for rupture risk assessment based on high-resolution vessel wall imaging

OBJECTIVE

We aimed to develop a comprehensive model that integrates the radiological, morphological, and clinical factors to assess rupture risk for intracranial aneurysms.

METHODS

We prospectively enrolled patients with intracranial saccular aneurysms who underwent high-resolution vessel wall imaging (HR-VWI) preoperatively. Clinical characteristics, aneurysm features and aneurysm wall enhancement scale (AWES) were recorded. AWES was categorized into three grades (no/faint/strong enhancement) by comparing AWE to enhancement of the pituitary infundibulum or choroid plexus on HR-VWI. Univariate and multivariate logistic regression analyses were performed to determine risk factors associated with aneurysmal rupture.

RESULTS

A total of 25 ruptured and 116 unruptured aneurysms were included. Multivariate logistic regression analysis revealed that non-ICA site (OR 6.25, 95% CI 1.35-28.30, P = 0.019), AWES (OR 5.99, 95% CI 2.51-14.29, P < 0.001) and daughter sac or lobulated shape (OR 6.22, 95% CI 1.68-23.16, P = 0.006) were independent factors associated with ruptured aneurysms. The "SAD" model was generated and named after the first letters of each of these factors. SAD scores of 0-4 predicted 0, 2%, 12%, 42% and 100% ruptured aneurysms, respectively. The area under the receiver operating characteristic curve for the SAD model was 0.8822.

CONCLUSION

The SAD model aids in distinguishing aneurysm rupture status and in managing unruptured aneurysms. Larger cohort studies are needed to confirm its applicability in predicting the rupture risk of unruptured aneurysms.

A Review of Artificial Intelligence in the Rupture Risk Assessment of Intracranial Aneurysms: Applications and Challenges

Intracranial aneurysms (IAs) are highly prevalent in the population, and their rupture poses a significant risk of death or disability. However, the treatment of aneurysms, whether through interventional embolization or craniotomy clipping surgery, is not always safe and carries a certain proportion of morbidity and mortality. Therefore, early detection and prompt intervention of IAs with a high risk of rupture is of notable clinical significance. Moreover, accurately predicting aneurysms that are likely to remain stable can help avoid the risks and costs of over-intervention, which also has considerable social significance. Recent advances in artificial intelligence (AI) technology offer promising strategies to assist clinical trials. This review will discuss the state-of-the-art AI applications for assessing the rupture risk of IAs, with a focus on achievements, challenges, and potential opportunities.

Automatic risk prediction of intracranial aneurysm on CTA image with convolutional neural networks and radiomics analysis

Background

Intracranial aneurysm (IA) is a nodular protrusion of the arterial wall caused by the localized abnormal enlargement of the lumen of a brain artery, which is the primary cause of subarachnoid hemorrhage. Accurate rupture risk prediction can effectively aid treatment planning, but conventional rupture risk estimation based on clinical information is subjective and time-consuming.

Methods

We propose a novel classification method based on the CTA images for differentiating aneurysms that are prone to rupture. The main contribution of this study is that the learning-based method proposed in this study leverages deep learning and radiomics features and integrates clinical information for a more accurate prediction of the risk of rupture. Specifically, we first extracted the provided aneurysm regions from the CTA images as 3D patches with the lesions located at their centers. Then, we employed an encoder using a 3D convolutional neural network (CNN) to extract complex latent features automatically. These features were then combined with radiomics features and clinical information. We further applied the LASSO regression method to find optimal features that are highly relevant to the rupture risk information, which is fed into a support vector machine (SVM) for final rupture risk prediction.

Results

The experimental results demonstrate that our classification method can achieve accuracy and AUC scores of 89.78% and 89.09%, respectively, outperforming all the alternative methods.

Discussion

Our study indicates that the incorporation of CNN and radiomics analysis can improve the prediction performance, and the selected optimal feature set can provide essential biomarkers for the determination of rupture risk, which is also of great clinical importance for individualized treatment planning and patient care of IA.

A deep-learning method for the end-to-end prediction of intracranial aneurysm rupture risk

It is critical to accurately predict the rupture risk of an intracranial aneurysm (IA) for timely and appropriate treatment because the fatality rate after rupture is 50 % . Existing methods relying on morphological features (e.g., height-width ratio) measured manually by neuroradiologists are labor intensive and have limited use for risk assessment. Therefore, we propose an end-to-end deep-learning method, called TransIAR net, to automatically learn the morphological features from 3D computed tomography angiography (CTA) data and accurately predict the status of IA rupture. We devise a multiscale 3D convolutional neural network (CNN) to extract the structural patterns of the IA and its neighborhood with a dual branch of shared network structures. Moreover, we learn the spatial dependence within the IA neighborhood with a transformer encoder. Our experiments demonstrated that the features learned by TransIAR are more effective and robust than handcrafted features, resulting in a 10 % - 15 % improvement in the accuracy of rupture status prediction.

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.

Predicting the rupture status of small middle cerebral artery aneurysms using random forest modeling

Objective

Small intracranial aneurysms are increasingly being detected; however, a prediction model for their rupture is rare. Random forest modeling was used to predict the rupture status of small middle cerebral artery (MCA) aneurysms with morphological features.

Methods

From January 2009 to June 2020, we retrospectively reviewed patients with small MCA aneurysms (<7 mm). The aneurysms were randomly split into training (70%) and internal validation (30%) cohorts. Additional independent datasets were used for the external validation of 78 small MCA aneurysms from another four hospitals. Aneurysm morphology was determined using computed tomography angiography (CTA). Prediction models were developed using the random forest and multivariate logistic regression.

Results

A total of 426 consecutive patients with 454 small MCA aneurysms (<7 mm) were included. A multivariate logistic regression analysis showed that size ratio (SR), aspect ratio (AR), and daughter dome were associated with aneurysm rupture, whereas aneurysm angle and multiplicity were inversely associated with aneurysm rupture. The areas under the receiver operating characteristic (ROC) curves (AUCs) of random forest models using the five independent risk factors in the training, internal validation, and external validation cohorts were 0.922, 0.889, and 0.92, respectively. The random forest model outperformed the logistic regression model (p = 0.048). A nomogram was developed to assess the rupture of small MCA aneurysms.

Conclusion

Random forest modeling is a good tool for evaluating the rupture status of small MCA aneurysms and may be considered for the management of small aneurysms.

A Review of Artificial Intelligence in Cerebrovascular Disease Imaging: Applications and Challenges

BACKGROUND

A variety of emerging medical imaging technologies based on artificial intelligence have been widely applied in many diseases, but they are still limitedly used in the cerebrovascular field even though the diseases can lead to catastrophic consequences.

OBJECTIVE

This work aims to discuss the current challenges and future directions of artificial intelligence technology in cerebrovascular diseases through reviewing the existing literature related to applications in terms of computer-aided detection, prediction and treatment of cerebrovascular diseases.

METHODS

Based on artificial intelligence applications in four representative cerebrovascular diseases including intracranial aneurysm, arteriovenous malformation, arteriosclerosis and moyamoya disease, this paper systematically reviews studies published between 2006 and 2021 in five databases: National Center for Biotechnology Information, Elsevier Science Direct, IEEE Xplore Digital Library, Web of Science and Springer Link. And three refinement steps were further conducted after identifying relevant literature from these databases.

RESULTS

For the popular research topic, most of the included publications involved computer-aided detection and prediction of aneurysms, while studies about arteriovenous malformation, arteriosclerosis and moyamoya disease showed an upward trend in recent years. Both conventional machine learning and deep learning algorithms were utilized in these publications, but machine learning techniques accounted for a larger proportion.

CONCLUSION

Algorithms related to artificial intelligence, especially deep learning, are promising tools for medical imaging analysis and will enhance the performance of computer-aided detection, prediction and treatment of cerebrovascular diseases.

An Integrated Model Combining Machine Learning and Deep Learning Algorithms for Classification of Rupture Status of IAs

Background

The rupture risk assessment of intracranial aneurysms (IAs) is clinically relevant. How to accurately assess the rupture risk of IAs remains a challenge in clinical decision-making.

Purpose

We aim to build an integrated model to improve the assessment of the rupture risk of IAs.

Materials and Methods

A total of 148 (39 ruptured and 109 unruptured) IA subjects were retrospectively computed with computational fluid dynamics (CFDs), and the integrated models were proposed by combining machine learning (ML) and deep learning (DL) algorithms. ML algorithms that include random forest (RF), k-nearest neighbor (KNN), XGBoost (XGB), support vector machine (SVM), and LightGBM were, respectively, adopted to classify ruptured and unruptured IAs. A Pointnet DL algorithm was applied to extract hemodynamic cloud features from the hemodynamic clouds obtained from CFD. Morphological variables and hemodynamic parameters along with the extracted hemodynamic cloud features were acted as the inputs to the classification models. The classification results with and without hemodynamic cloud features are computed and compared.

Results

Without consideration of hemodynamic cloud features, the classification accuracy of RF, KNN, XGB, SVM, and LightGBM was 0.824, 0.759, 0.839, 0.860, and 0.829, respectively, and the AUCs of them were 0.897, 0.584, 0.892, 0.925, and 0.890, respectively. With the consideration of hemodynamic cloud features, the accuracy successively increased to 0.908, 0.873, 0.900, 0.926, and 0.917. Meanwhile, the AUCs reached 0.952, 0.881, 0.950, 0.969, and 0.965 eventually. Adding consideration of hemodynamic cloud features, the SVM could perform best with the highest accuracy of 0.926 and AUC of 0.969, respectively.

Conclusion

The integrated model combining ML and DL algorithms could improve the classification of IAs. Adding consideration of hemodynamic cloud features could bring more accurate classification, and hemodynamic cloud features were important for the discrimination of ruptured IAs.

Machine Learning for Rupture Risk Prediction of Intracranial Aneurysms: Challenging the PHASES Score in Geographically Constrained Areas

Intracranial aneurysms represent a potentially life-threatening condition and occur in 3–5% of the population. They are increasingly diagnosed due to the broad application of cranial magnetic resonance imaging and computed tomography in the context of headaches, vertigo, and other unspecific symptoms. For each affected individual, it is utterly important to estimate the rupture risk of the respective aneurysm. However, clinically applied decision tools, such as the PHASES score, remain insufficient. Therefore, a machine learning approach assessing the rupture risk of intracranial aneurysms is proposed in our study. For training and evaluation of the algorithm, data from a single neurovascular center was used, comprising 446 aneurysms (221 ruptured, 225 unruptured). The machine learning model was then compared with the PHASES score and proved superior in accuracy (0.7825), F1-score (0.7975), sensitivity (0.8643), specificity (0.7022), positive predictive value (0.7403), negative predictive value (0.8404), and area under the curve (0.8639). The frequency distributions of the predicted rupture probabilities and the PHASES score were analyzed. A symmetry can be observed between the rupture probabilities, with a symmetry axis at 0.5. A feature importance analysis reveals that the body mass index, consumption of anticoagulants, and harboring vessel are regarded as the most important features when assessing the rupture risk. On the other hand, the size of the aneurysm, which is weighted most in the PHASES score, is regarded as less important. Based on our findings we discuss the potential role of the model for clinical practice in geographically confined aneurysm patients.

Detection and analysis of cerebral aneurysms based on X-ray rotational angiography - the CADA 2020 challenge

The Cerebral Aneurysm Detection and Analysis (CADA) challenge was organized to support the development and benchmarking of algorithms for detecting, analyzing, and risk assessment of cerebral aneurysms in X-ray rotational angiography (3DRA) images. 109 anonymized 3DRA datasets were provided for training, and 22 additional datasets were used to test the algorithmic solutions. Cerebral aneurysm detection was assessed using the F2 score based on recall and precision, and the fit of the delivered bounding box was assessed using the distance to the aneurysm. The segmentation quality was measured using the Jaccard index and a combination of different surface distance measures. Systematic errors were analyzed using volume correlation and bias. Rupture risk assessment was evaluated using the F2 score. 158 participants from 22 countries registered for the CADA challenge. The U-Net-based detection solutions presented by the community show similar accuracy compared to experts (F2 score 0.92), with a small number of missed aneurysms with diameters smaller than 3.5 mm. In addition, the delineation of these structures, based on U-Net variations, is excellent, with a Jaccard score of 0.92. The rupture risk estimation methods achieved an F2 score of 0.71. The performance of the detection and segmentation solutions is equivalent to that of human experts. The best results are obtained in rupture risk estimation by combining different image-based, morphological, and computational fluid dynamic parameters using machine learning methods. Furthermore, we evaluated the best methods pipeline, from detecting and delineating the vessel dilations to estimating the risk of rupture. The chain of these methods achieves an F2-score of 0.70, which is comparable to applying the risk prediction to the ground-truth delineation (0.71).

Artificial Intelligence-Enabled Medical Analysis for Intracranial Cerebral Hemorrhage Detection and Classification

Intracranial hemorrhage (ICH) becomes a crucial healthcare emergency, which requires earlier detection and accurate assessment. Owing to the increased death rate (around 40%), the earlier recognition and classification of disease using computed tomography (CT) images are necessary to ensure a favourable prediction and restrain the existence of neurologic deficits. Since the manual diagnosis approach is time-consuming, automated ICH detection and classification models using artificial intelligence (AI) models are required. With this motivation, this study introduces an AI-enabled medical analysis tool for ICH detection and classification (AIMA-ICHDC) using CT images. The proposed AIMA-ICHDC technique aims at identifying the presence of ICH and identifying the different grades. In addition, the AIMA-ICHDC technique involves the design of glowworm swarm optimization with fuzzy entropy clustering (GSO-FEC) technique for the segmentation process. Besides, the VGG-19 model was executed for generating a collection of feature vectors and the optimal mixed-kernel-based extreme learning machine (OMKELM) model is utilized as a classifier. To optimally select the weight parameter of the MKELM technique, the coyote optimization algorithm (COA) was utilized. A wide range of simulation analyses are carried out under varying aspects. As part of the AIMA-ICHDC method, ICH can be detected and graded using a single sample. For segmentation, the AIMA-ICHDC technique uses the GSO-FEC method, which is the design of glowworm swarm optimization (GSO). The comparative outcomes highlighted the betterment of the AIMA-ICHDC technique compared to the recent state-of-the-art ICH classification approaches in terms of several measures.

Artificial Intelligence Applications in Intracranial Aneurysm: Achievements, Challenges and Opportunities

Intracranial aneurysms present in about 3% of the general population and the number of detected aneurysms is continuously rising with the advances in imaging techniques. Intracranial aneurysm rupture carries a high risk of death or permanent disabilities; therefore assessment of the intracranial aneurysm along the entire course is of great clinical importance. Given the outstanding performance of artificial intelligence (AI) in image-based tasks, many AI-based applications have emerged in recent years for the assessment of intracranial aneurysms. In this review we will summarize the state-of-the-art of AI applications in intracranial aneurysms, emphasizing the achievements, and exploring the challenges. We will also discuss the future prospects and potential opportunities. This article provides an updated view of the AI applications in intracranial aneurysms and may act as a basis for guiding the related future works.

Morphology-aware multi-source fusion-based intracranial aneurysms rupture prediction

OBJECTIVES

We proposed a new approach to train deep learning model for aneurysm rupture prediction which only uses a limited amount of labeled data.

METHOD

Using segmented aneurysm mask as input, a backbone model was pretrained using a self-supervised method to learn deep embeddings of aneurysm morphology from 947 unlabeled cases of angiographic images. Subsequently, the backbone model was finetuned using 120 labeled cases with known rupture status. Clinical information was integrated with deep embeddings to further improve prediction performance. The proposed model was compared with radiomics and conventional morphology models in prediction performance. An assistive diagnosis system was also developed based on the model and was tested with five neurosurgeons.

RESULT

Our method achieved an area under the receiver operating characteristic curve (AUC) of 0.823, outperforming deep learning model trained from scratch (0.787). By integrating with clinical information, the proposed model's performance was further improved to AUC = 0.853, making the results significantly better than model based on radiomics (AUC = 0.805, p = 0.007) or model based on conventional morphology parameters (AUC = 0.766, p = 0.001). Our model also achieved the highest sensitivity, PPV, NPV, and accuracy among the others. Neurosurgeons' prediction performance was improved from AUC=0.877 to 0.945 (p = 0.037) with the assistive diagnosis system.

CONCLUSION

Our proposed method could develop competitive deep learning model for rupture prediction using only a limited amount of data. The assistive diagnosis system could be useful for neurosurgeons to predict rupture.

KEY POINTS

• A self-supervised learning method was proposed to mitigate the data-hungry issue of deep learning, enabling training deep neural network with a limited amount of data. • Using the proposed method, deep embeddings were extracted to represent intracranial aneurysm morphology. Prediction model based on deep embeddings was significantly better than conventional morphology model and radiomics model. • An assistive diagnosis system was developed using deep embeddings for case-based reasoning, which was shown to significantly improve neurosurgeons' performance to predict rupture.

Prediction and Risk Assessment Models for Subarachnoid Hemorrhage: A Systematic Review on Case Studies

Subarachnoid hemorrhage (SAH) is one of the major health issues known to society and has a higher mortality rate. The clinical factors with computed tomography (CT), magnetic resonance image (MRI), and electroencephalography (EEG) data were used to evaluate the performance of the developed method. In this paper, various methods such as statistical analysis, logistic regression, machine learning, and deep learning methods were used in the prediction and detection of SAH which are reviewed. The advantages and limitations of SAH prediction and risk assessment methods are also being reviewed. Most of the existing methods were evaluated on the collected dataset for the SAH prediction. In some researches, deep learning methods were applied, which resulted in higher performance in the prediction process. EEG data were applied in the existing methods for the prediction process, and these methods demonstrated higher performance. However, the existing methods have the limitations of overfitting problems, imbalance data problems, and lower efficiency in feature analysis. The artificial neural network (ANN) and support vector machine (SVM) methods have been applied for the prediction process, and considerably higher performance is achieved by using this method.

Machine Learning and Intracranial Aneurysms: From Detection to Outcome Prediction

Machine learning (ML) is a rapidly rising research tool in biomedical sciences whose applications include segmentation, classification, disease detection, and outcome prediction. With respect to traditional statistical methods, ML algorithms have the potential to learn and improve their predictive performance when fed with large data sets without the need of being specifically programmed. In recent years, this technology has been increasingly applied for tackling clinical issues in intracranial aneurysm (IA) research. Several studies attempted to provide reliable models for enhanced aneurysm detection. Convolutional neural networks trained with variable degrees of human interaction on data from diverse imaging modalities showed high sensitivity in aneurysm detection tasks, also outperforming expert image analysis. Algorithms were also shown to differentiate ruptured from unruptured IAs, with however limited clinical relevance. For prediction of rupture and stability assessment, ML was preliminarily shown to achieve better performance compared to conventional statistical methods and existing risk scores. ML-based complication and functional outcome prediction in the event of SAH have been more extensively reported, in contrast with periprocedural outcome investigation in unruptured IA patients. ML has the potential to be a game changer in IA patient management. Currently clinical translation of experimental results is limited.

Development and assessment of machine learning models for predicting recurrence risk after endovascular treatment in patients with intracranial aneurysms

Intracranial aneurysms (IAs) remain a major public health concern and endovascular treatment (EVT) has become a major tool for managing IAs. However, the recurrence rate of IAs after EVT is relatively high, which may lead to the risk for aneurysm re-rupture and re-bleed. Thus, we aimed to develop and assess prediction models based on machine learning (ML) algorithms to predict recurrence risk among patients with IAs after EVT in 6 months. Patient population included patients with IAs after EVT between January 2016 and August 2019 in Hunan Provincial People's Hospital, and an adaptive synthetic (ADASYN) sampling approach was applied for the entire imbalanced dataset. We developed five ML models and assessed the models. In addition, we used SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanation (LIME) algorithms to determine the importance of the selected features and interpret the ML models. A total of 425 IAs were enrolled into this study, and 66 (15.5%) of which recurred in 6 months. Among the five ML models, gradient boosting decision tree (GBDT) model performed best. The area under curve (AUC) of the GBDT model on the testing set was 0.842 (sensitivity: 81.2%; specificity: 70.4%). Our study firstly demonstrated that ML-based models can serve as a reliable tool for predicting recurrence risk in patients with IAs after EVT in 6 months, and the GBDT model showed the optimal prediction performance.

Current Perspectives of Artificial Intelligence in Pediatric Neuroradiology: An Overview

Artificial Intelligence, Machine Learning, and myriad related techniques are becoming ever more commonplace throughout industry and society, and radiology is by no means an exception. It is essential for every radiologists of every subspecialty to gain familiarity and confidence with these techniques as they become increasingly incorporated into the routine practice in both academic and private practice settings. In this article, we provide a brief review of several definitions and techniques that are commonly used in AI, and in particular machine vision, and examples of how they are currently being applied to the setting of clinical neuroradiology. We then review the unique challenges that the adoption and application of faces within the subspecialty of pediatric neuroradiology, and how these obstacles may be overcome. We conclude by presenting specific examples of how AI is currently being applied within the field of pediatric neuroradiology and the potential opportunities that are available for future applications.

Profiling of T Cell Receptor β-Chain Complimentary Determining Regions 3 Repertoire in Subarachnoid Hemorrhage Patients Using High-Throughput Sequencing

Objective

The adaptive immune response following subarachnoid hemorrhage (SAH) is not well understood. We evaluated and compared the T cell receptor (TCR) immune repertoire of good-grade and poor-grade SAH patients to elucidate the T cell immunology after ictus.

Methods

Peripheral blood from six SAH patients was collected at two different times, admission and at the 7-day follow-up. Composition and variation of the TCR β-chain (TCRB) complimentary determining regions (CDR) 3 repertoire was examined using high-throughput sequencing; the analysis was based on sampling time and disease severity (good vs. poor-grade SAH).

Results

Clonality at admission and follow-up were 0.059 (0.037–0.038) and 0.027 (0.014–0.082) (median, 25th–75th percentile). Poor-grade SAH (0.025 [0.011–0.038]) was associated with significantly lower clonality than good-grade SAH (0.095 [0.079–0.101]). Poor-grade SAH patients had higher diversity scores than good-grade SAH patients. CDR length was shorter in good-grade SAH vs. poor-grade SAH. Differences in clonotype distribution were more prominent in TCRBV gene segments than TCRBJ segments. TCRBV19-01/TCRBJ02-04 and TCRBV28-01/TCRBJ02-04 were the most increased and the most decreased V-J pairs in the 7-day follow-up compared to admission in good-grade SAH. The most increased and decreased V-J pairs in poor-grade SAH patients were TCRBV28-01/TCRBJ02-06 and TCRBV30-01/TCRBJ02-04, respectively.

Conclusion

The TCRB repertoire is dynamic in nature following SAH. TCRB repertoire may facilitate our understanding of adaptive immune response according to SAH severity.

Easily Created Prediction Model Using Automated Artificial Intelligence Framework (Prediction One, Sony Network Communications Inc., Tokyo, Japan) for Subarachnoid Hemorrhage Outcomes Treated by Coiling and Delayed Cerebral Ischemia

Introduction Reliable prediction models of subarachnoid hemorrhage (SAH) outcomes and delayed cerebral ischemia (DCI) are needed to decide the treatment strategy. Automated artificial intelligence (AutoAI) is attractive, but there are few reports on AutoAI-based models for SAH functional outcomes and DCI. We herein made models using an AutoAI framework, Prediction One (Sony Network Communications Inc., Tokyo, Japan), and compared it to other previous statistical prediction scores. Methods We used an open dataset of 298 SAH patients, who were with non-severe neurological grade and treated by coiling. Modified Rankin Scale 0-3 at six months was defined as a favorable functional outcome and DCI occurrence as another outcome. We randomly divided them into a 248-patient training dataset and a 50-patient test dataset. Prediction One made the model using training dataset with 5-fold cross-validation. We evaluated the model using the test dataset and compared the area under the curves (AUCs) of the created models. Those of the modified SAFIRE score and the Fisher computed tomography (CT) scale to predict the outcomes. Results The AUCs of the AutoAI-based models for functional outcome in the training and test dataset were 0.994 and 0.801, and those for the DCI occurrence were 0.969 and 0.650. AUCs for functional outcome calculated using modified SAFIRE score were 0.844 and 0.892. Those for the DCI occurrence calculated using the Fisher CT scale were 0.577 and 0.544. Conclusions We easily and quickly made AutoAI-based prediction models. The models' AUCs were not inferior to the previous prediction models despite the easiness.

Machine Learning-Based Prediction of Small Intracranial Aneurysm Rupture Status Using CTA-Derived Hemodynamics: A Multicenter Study

BACKGROUND AND PURPOSE

Small intracranial aneurysms are being increasingly detected while the rupture risk is not well-understood. We aimed to develop rupture-risk models of small aneurysms by combining clinical, morphologic, and hemodynamic information based on machine learning techniques and to test the models in external validation datasets.

MATERIALS AND METHODS

From January 2010 to December 2016, five hundred four consecutive patients with only small aneurysms (<5 mm) detected by CTA and invasive cerebral angiography (or surgery) were retrospectively enrolled and randomly split into training (81%) and internal validation (19%) sets to derive and validate the proposed machine learning models (support vector machine, random forest, logistic regression, and multilayer perceptron). Hemodynamic parameters were obtained using computational fluid dynamics simulation. External validation was performed in other hospitals to test the models.

RESULTS

The support vector machine performed the best with areas under the curve of 0.88 (95% CI, 0.85-0.92) and 0.91 (95% CI, 0.74-0.98) in the training and internal validation datasets, respectively. Feature ranks suggested hemodynamic parameters, including stable flow pattern, concentrated inflow streams, and a small (<50%) flow-impingement zone, and the oscillatory shear index coefficient of variation, were the best predictors of aneurysm rupture. The support vector machine showed an area under the curve of 0.82 (95% CI, 0.69-0.94) in the external validation dataset, and no significant difference was found for the areas under the curve between internal and external validation datasets (P = .21).

CONCLUSIONS

This study revealed that machine learning had a good performance in predicting the rupture status of small aneurysms in both internal and external datasets. Aneurysm hemodynamic parameters were regarded as the most important predictors.

The Role of Consecutive Plasma Copeptin Levels in the Screening of Delayed Cerebral Ischemia in Poor-Grade Subarachnoid Hemorrhage

The prognostic value of copeptin in subarachnoid hemorrhage (SAH) has been reported, but the prognosis was largely affected by the initial clinical severity. Thus, the previous studies are not very useful in predicting delayed cerebral ischemia (DCI) in poor-grade SAH patients. Here, we first investigated the feasibility of predicting DCI in poor-grade SAH based on consecutive measurements of plasma copeptin. We measured copeptin levels of 86 patients on days 1, 3, 5, 7, 9, 11, and 13 using ELISA. The primary outcome was the association between consecutive copeptin levels and DCI development. The secondary outcomes were comparison of copeptin with C-reactive protein (CRP) in predicting DCI. Additionally, we compared the prognostic value of transcranial Doppler ultrasonography (TCD) with copeptin using TCD alone to predict DCI. Increased copeptin (OR = 1.022, 95% CI: 1.008–1.037) and modified Fisher scale IV (OR = 2.841; 95% CI: 0.998–8.084) were closely related to DCI. Consecutive plasma copeptin measurements showed significant differences between DCI and non-DCI groups (p < 0.001). Higher CRP and DCI appeared to show a correlation, but it was not statistically significant. Analysis of copeptin changes with TCD appeared to predict DCI better than TCD alone with AUCROC differences of 0.072. Consecutive measurements of plasma copeptin levels facilitate the screening of DCI in poor-grade SAH patients.

Multi-View Convolutional Neural Networks in Rupture Risk Assessment of Small, Unruptured Intracranial Aneurysms

Auto-detection of cerebral aneurysms via convolutional neural network (CNN) is being increasingly reported. However, few studies to date have accurately predicted the risk, but not the diagnosis itself. We developed a multi-view CNN for the prediction of rupture risk involving small unruptured intracranial aneurysms (UIAs) based on three-dimensional (3D) digital subtraction angiography (DSA). The performance of a multi-view CNN-ResNet50 in accurately predicting the rupture risk (high vs. non-high) of UIAs in the anterior circulation measuring less than 7 mm in size was compared with various CNN architectures (AlexNet and VGG16), with similar type but different layers (ResNet101 and ResNet152), and single image-based CNN (single-view ResNet50). The sensitivity, specificity, and overall accuracy of risk prediction were estimated and compared according to CNN architecture. The study included 364 UIAs in training and 93 in test datasets. A multi-view CNN-ResNet50 exhibited a sensitivity of 81.82 (66.76–91.29)%, a specificity of 81.63 (67.50–90.76)%, and an overall accuracy of 81.72 (66.98–90.92)% for risk prediction. AlexNet, VGG16, ResNet101, ResNet152, and single-view CNN-ResNet50 showed similar specificity. However, the sensitivity and overall accuracy were decreased (AlexNet, 63.64% and 76.34%; VGG16, 68.18% and 74.19%; ResNet101, 68.18% and 73.12%; ResNet152, 54.55% and 72.04%; and single-view CNN-ResNet50, 50.00% and 64.52%) compared with multi-view CNN-ResNet50. Regarding F1 score, it was the highest in multi-view CNN-ResNet50 (80.90 (67.29–91.81)%). Our study suggests that multi-view CNN-ResNet50 may be feasible to assess the rupture risk in small-sized UIAs.

Multidimensional predicting model of intracranial aneurysm stability with backpropagation neural network: a preliminary study

OBJECTIVES

The stability of intracranial aneurysms (IAs) may involve in multidimensional factors. Backpropagation (BP) neural network could be adopted to support clinical work. This preliminary study aimed to delve into the feasibility of BP neural network in assessing the risk of IA rupture/growth and to prove the advantage of multidimensional model over single/double-dimensional model.

METHODS

Thirty-six IA patients were recruited from a prospective registration study (ChiCTR1900024547). All patients were followed up until aneurysm ruptured/grew or 36 months after being diagnosed with the IAs. The multidimensional data regarding clinical, morphological, and hemodynamic characteristics were acquired. Hemodynamic analyses were conducted with patient-specific models. Based on these characteristics, seven models were built with BP neural network (the ratio of training set to validation set as 8:1). The area under curves (AUC) was calculated for subsequent comparison.

RESULTS

Forty-five characteristics were determined from 36 patients with 37 IAs. In the models based on the single dimension of IA characteristics, only morphological characteristics exhibited high performance in assessing 3-year IA stability (AUC = 0.703, P = 0.035). Among the models integrating two dimensions of IA characteristics, clinical-morphological (AUC = 0.731, P = 0.016), clinical-hemodynamic (AUC = 0.702, P = 0.036), and morphological-hemodynamic (AUC = 0.785, P = 0.003) models were capable of assessing the risk of 3-year IA rupture/growth. Moreover, the models including all three dimensions exhibited the maximum predicting significance (AUC = 0.811, P = 0.001).

CONCLUSION

The present preliminary study reported that BP neural network might support assessing the 3-year stability of IAs. Models based on multidimensional characteristics could improve the assessment accuracy for IA rupture/growth.

CT Angiography-Based Radiomics for Classification of Intracranial Aneurysm Rupture

Background: Intracranial aneurysm rupture is a devastating medical event with a high morbidity and mortality rate. Thus, timely detection and management are critical. The present study aimed to identify the aneurysm radiomics features associated with rupture and to build and evaluate a radiomics classification model of aneurysm rupture. Methods: Radiomics analysis was applied to CT angiography (CTA) images of 393 patients [152 (38.7%) with ruptured aneurysms]. Patients were divided at a ratio of 7:3 into retrospective training (n = 274) and prospective test (n = 119) cohorts. A total of 1,229 radiomics features were automatically calculated from each aneurysm. The feature number was systematically reduced, and the most important classifying features were selected. A logistic regression model was constructed using the selected features and evaluated on training and test cohorts. Radiomics score (Rad-score) was calculated for each patient and compared between ruptured and unruptured aneurysms. Results: Nine radiomics features were selected from the CTA images and used to build the logistic regression model. The radiomics model has shown good performance in the classification of the aneurysm rupture on training and test cohorts [area under the receiver operating characteristic curve: 0.92 [95% confidence interval CI: 0.89-0.95] and 0.86 [95% CI: 0.80-0.93], respectively, p < 0.001]. Rad-score showed statistically significant differences between ruptured and unruptured aneurysms (median, 2.50 vs. -1.60 and 2.35 vs. -1.01 on training and test cohorts, respectively, p < 0.001). Conclusion: The results indicated the potential of aneurysm radiomics features for automatic classification of aneurysm rupture on CTA images.

Nomogram for Stability Stratification of Small Intracranial Aneurysm Based on Clinical and Morphological Risk Factors

Background and Purpose: Stability stratification of intracranial aneurysms (IAs) is crucial for individualized clinical management, especially for small IAs. We aim to develop and validate a nomogram based on clinical and morphological risk factors for individualized instability stratification of small IAs.

Methods: Six hundred fifty-eight patients with unstable (n = 293) and stable (n = 416) IAs <7 mm were randomly divided into derivation and validation cohorts. Twelve clinical risk factors and 18 aneurysm morphological risk factors were extracted. Combined with important risk factors, a clinical-morphological predictive nomogram was developed. The nomogram performance was evaluated in the derivation and the validation cohorts in terms of discrimination, calibration, and clinical usefulness.

Results: Five independent instability-related risk factors were included in the nomogram: location, irregularity, side/bifurcation type, flow angle, and height-to-width ratio. In the derivation cohort, the area under the curve (95% CI) of the nomogram was 0.803 (95% CI, 0.764–0.842), and good agreement between predicted instability risk and actual instability status could be detected in the calibration plot. The nomogram also exhibited good discriminations and calibration in the validation cohort: the area under the curve (95% CI) was 0.744 (95% CI, 0.677–0.812). Small IAs with scores <90 were considered to have low risk of instability, and those with scores of 90 or greater were considered to have high risk of instability.

Conclusions: The nomogram based on clinical and morphological risk factors can be used as a convenient tool to facilitate individualized decision-making in the management of small IAs.

Rupture Risk Assessment for Cerebral Aneurysm Using Interpretable Machine Learning on Multidimensional Data

Background: Assessment of cerebral aneurysm rupture risk is an important task, but it remains challenging. Recent works applying machine learning to rupture risk evaluation presented positive results. Yet they were based on limited aspects of data, and lack of interpretability may limit their use in clinical setting. We aimed to develop interpretable machine learning models on multidimensional data for aneurysm rupture risk assessment. Methods: Three hundred seventy-four aneurysms were included in the study. Demographic, medical history, lifestyle behaviors, lipid profile, and morphologies were collected for each patient. Prediction models were derived using machine learning methods (support vector machine, artificial neural network, and XGBoost) and conventional logistic regression. The derived models were compared with the PHASES score method. The Shapley Additive Explanations (SHAP) analysis was applied to improve the interpretability of the best machine learning model and reveal the reasoning behind the predictions made by the model. Results: The best machine learning model (XGBoost) achieved an area under the receiver operating characteristic curve of 0.882 [95% confidence interval (CI) = 0.838-0.927], significantly better than the logistic regression model (0.779; 95% CI = 0.729-0.829; P = 0.002) and the PHASES score method (0.758; 95% CI = 0.713-0.800; P = 0.001). Location, size ratio, and triglyceride level were the three most important features in predicting rupture. Two typical cases were analyzed to demonstrate the interpretability of the model. Conclusions: This study demonstrated the potential of using machine learning for aneurysm rupture risk assessment. Machine learning models performed better than conventional statistical model and the PHASES score method. The SHAP analysis can improve the interpretability of machine learning models and facilitate their use in a clinical setting.

Machine learning in neurosurgery: a global survey

Background

Recent technological advances have led to the development and implementation of machine learning (ML) in various disciplines, including neurosurgery. Our goal was to conduct a comprehensive survey of neurosurgeons to assess the acceptance of and attitudes toward ML in neurosurgical practice and to identify factors associated with its use.

Methods

The online survey consisted of nine or ten mandatory questions and was distributed in February and March 2019 through the European Association of Neurosurgical Societies (EANS) and the Congress of Neurosurgeons (CNS).

Results

Out of 7280 neurosurgeons who received the survey, we received 362 responses, with a response rate of 5%, mainly in Europe and North America. In total, 103 neurosurgeons (28.5%) reported using ML in their clinical practice, and 31.1% in research. Adoption rates of ML were relatively evenly distributed, with 25.6% for North America, 30.9% for Europe, 33.3% for Latin America and the Middle East, 44.4% for Asia and Pacific and 100% for Africa with only two responses. No predictors of clinical ML use were identified, although academic settings and subspecialties neuro-oncology, functional, trauma and epilepsy predicted use of ML in research. The most common applications were for predicting outcomes and complications, as well as interpretation of imaging.

Conclusions

This report provides a global overview of the neurosurgical applications of ML. A relevant proportion of the surveyed neurosurgeons reported clinical experience with ML algorithms. Future studies should aim to clarify the role and potential benefits of ML in neurosurgery and to reconcile these potential advantages with bioethical considerations.

Easily created prediction model using deep learning software (Prediction One, Sony Network Communications Inc.) for subarachnoid hemorrhage outcomes from small dataset at admission

BACKGROUND

Reliable prediction models of subarachnoid hemorrhage (SAH) outcomes are needed for decision-making of the treatment. SAFIRE score using only four variables is a good prediction scoring system. However, making such prediction models needs a large number of samples and time-consuming statistical analysis. Deep learning (DL), one of the artificial intelligence, is attractive, but there were no reports on prediction models for SAH outcomes using DL. We herein made a prediction model using DL software, Prediction One (Sony Network Communications Inc., Tokyo, Japan) and compared it to SAFIRE score.

METHODS

We used 153 consecutive aneurysmal SAH patients data in our hospital between 2012 and 2019. Modified Rankin Scale (mRS) 0-3 at 6 months was defined as a favorable outcome. We randomly divided them into 102 patients training dataset and 51 patients external validation dataset. Prediction one made the prediction model using the training dataset with internal cross-validation. We used both the created model and SAFIRE score to predict the outcomes using the external validation set. The areas under the curve (AUCs) were compared.

RESULTS

The model made by Prediction One using 28 variables had AUC of 0.848, and its AUC for the validation dataset was 0.953 (95%CI 0.900-1.000). AUCs calculated using SAFIRE score were 0.875 for the training dataset and 0.960 for the validation dataset, respectively.

CONCLUSION

We easily and quickly made prediction models using Prediction One, even with a small single-center dataset. The accuracy of the model was not so inferior to those of previous statistically calculated prediction models.

A preliminary investigation of radiomics differences between ruptured and unruptured intracranial aneurysms

OBJECTIVES

Prediction of intracranial aneurysm rupture is important in the management of unruptured aneurysms. The application of radiomics in predicting aneurysm rupture remained largely unexplored. This study aims to evaluate the radiomics differences between ruptured and unruptured aneurysms and explore its potential use in predicting aneurysm rupture.

METHODS

One hundred twenty-two aneurysms were included in the study (93 unruptured). Morphological and radiomics features were extracted for each case. Statistical analysis was performed to identify significant features which were incorporated into prediction models constructed with a machine learning algorithm. To investigate the usefulness of radiomics features, three models were constructed and compared. The baseline model A was constructed with morphological features, while model B was constructed with addition of radiomics shape features and model C with more radiomics features. Multivariate analysis was performed for the ten most important variables in model C to identify independent risk factors. A simplified model based on independent risk factors was constructed for clinical use.

RESULTS

Five morphological features and 89 radiomics features were significantly associated with rupture. Model A, model B, and model C achieved the area under the receiver operating characteristic curve of 0.767, 0.807, and 0.879, respectively. Model C was significantly better than model A and model B (p < 0.001). Multivariate analysis identified two radiomics features which were used to construct the simplified model showing an AUROC of 0.876.

CONCLUSIONS

Radiomics signatures were different between ruptured and unruptured aneurysms. The use of radiomics features, especially texture features, may significantly improve rupture prediction performance.

KEY POINTS

• Significant radiomics differences exist between ruptured and unruptured intracranial aneurysms. • Radiomics shape features can significantly improve rupture prediction performance over conventional morphology-based prediction model. The inclusion of histogram and texture radiomics features can further improve the performance. • A simplified model with two variables achieved a similar level of performance as the more complex ones. Our prediction model can serve as a promising tool for the risk management of intracranial aneurysms.

Monitoring of Delayed Cerebral Ischemia in Patients with Subarachnoid Hemorrhage via Near-Infrared Spectroscopy

We investigated the role of near infrared spectroscopy (NIRS) in identifying delayed cerebral ischemia (DCI) in patients with subarachnoid hemorrhage (SAH). We measured the cerebral regional oxygen saturation (rSO2) continuously for 14 days. The differences in rSO2 according to DCI were analyzed. We also compared the diagnostic accuracy of NIRS and transcranial Doppler ultrasonography (TCD) for DCI detection using the area under receiver operator characteristic (ROC) curve. Fifty-two patients treated with coil embolization were enrolled, including 18 with DCI (34.6%) and 34 without DCI (65.4%). Significant differences in rSO2 levels were observed from days 7 to 9. The rSO2 level was 60.95 (58.10-62.30) at day 7 in the DCI vs. 63.90 (62.50-67.10) in the non-DCI patients. By day 8, it was 59.50 (56.90-64.50) in the DCI vs. 63.30 (59.70-68.70) in the non-DCI cases. By day 9, it was 61.85 (59.40-65.20) in the DCI vs. 66.00 (62.70-68.30) in the non-DCI. A decline of >12.7% in SO2 rate yielded a sensitivity of 94.44% (95% CI: 72.7-99.9%) and a specificity of 70.59% (95% CI: 52.5-84.9%) for identifying DCI. Changes in NIRS tended to yield better diagnostic accuracy than TCD, but were not statistically significant. NIRS is a feasible method for real-time detection of DCI.

Stability Assessment of Intracranial Aneurysms Using Machine Learning Based on Clinical and Morphological Features

Machine learning (ML) as a novel approach could help clinicians address the challenge of accurate stability assessment of unruptured intracranial aneurysms (IAs). We developed multiple ML models for IA stability assessment and compare their performances. We enrolled 1897 consecutive patients with unstable (n = 528) and stable (n = 1539) IAs. Thirteen patient-specific clinical features and eighteen aneurysm morphological features were extracted to generate support vector machine (SVM), random forest (RF), and feed-forward artificial neural network (ANN) models. The discriminatory performances of the models were compared with statistical logistic regression (LR) model and the PHASES score in IA stability assessment. Based on the receiver operating characteristic (ROC) curve and area under the curve (AUC) values for each model in the test set, the AUC values for RF, SVM, and ANN were 0.850 (95% CI 0.806-0.893), 0.858 (95 %CI 0.816-0.900), and 0.867 (95% CI 0.828-0.906), demonstrating good discriminatory ability. All ML models exhibited superior performance compared with the statistical LR and the PHASES score (the AUC values were 0.830 and 0.589, respectively; RF versus PHASES, P < 0.001; RF versus LR, P = 0.038). Important features contributing to the stability discrimination included three clinical features (location, sidewall/bifurcation type, and presence of symptoms) and three morphological features (undulation index, height-width ratio, and irregularity). These findings demonstrate the potential of ML to augment the clinical decision-making process for IA stability assessment, which may enable more optimal management for patients with IAs in the future.

Development and validation of machine learning prediction model based on computed tomography angiography-derived hemodynamics for rupture status of intracranial aneurysms: a Chinese multicenter study

OBJECTIVES

To build models based on conventional logistic regression (LR) and machine learning (ML) algorithms combining clinical, morphological, and hemodynamic information to predict individual rupture status of unruptured intracranial aneurysms (UIAs), afterwards tested in internal and external validation datasets.

METHODS

Patients with intracranial aneurysms diagnosed by computed tomography angiography and confirmed by invasive cerebral angiograph or clipping surgery were included. The prediction models were developed based on clinical, aneurysm morphological, and hemodynamic parameters by conventional LR and ML methods.

RESULTS

The training, internal validation, and external validation cohorts were composed of 807 patients, 200 patients, and 108 patients, respectively. The area under curves (AUCs) of conventional LR models 1 (clinical), 2 (clinical and aneurysm morphological), and 3 (clinical, aneurysm morphological and hemodynamic characteristics) were 0.608, 0.765, and 0.886, respectively (all p < 0.05). The AUCs of ML models using random forest (RF), multilayer perceptron (MLP), and support vector machine (SVM) were 0.871, 0.851, and 0.863, respectively. There were no difference among AUCs of conventional LR, RF, and SVM (all p > 0.05/6), while the AUC of MLP was lower than that of conventional LR (p = 0.0055).

CONCLUSION

Hemodynamic parameters play an important role in the prediction performance of the models. ML methods cannot outperform conventional LR in prediction models for rupture status of UIAs integrating clinical, aneurysm morphological, and hemodynamic parameters.

KEY POINTS

• The addition of hemodynamic parameters can improve prediction performance for rupture status of unruptured intracranial aneurysms. • Machine learning algorithms cannot outperform conventional logistic regression in prediction models for rupture status integrating clinical, aneurysm morphological, and hemodynamic parameters. • Models integrating clinical, aneurysm morphological, and hemodynamic parameters may help choose the optimal management.

Characterization of the TCR β Chain CDR3 Repertoire in Subarachnoid Hemorrhage Patients with Delayed Cerebral Ischemia

Little is known of the adaptive immune response to subarachnoid hemorrhage (SAH). This study was the first to investigate whether T cell receptor (TCR) immune repertoire may provide a better understanding of T cell immunology in delayed cerebral ischemia (DCI). We serially collected peripheral blood in five SAH patients with DCI. High-throughput sequencing was used to analyze the TCR β chain (TCRB) complimentary determining regions (CDR) 3 repertoire. We evaluated the compositions and variations of the repertoire between admission and the DCI period, for severe DCI and non-severe DCI patients. Clonality did not differ significantly between admission and DCI. Severe DCI patients had significantly lower clonality than non-severe DCI patients (p value = 0.019). A read frequency of 0.005% ≤ - < 0.05% dominated the clonal expansion in non-severe DCI patients. Regarding repertoire diversity, severe DCI had a higher diversity score on admission than non-severe DCI. The CDR3 lengths were similar between admission and DCI. Among 728 annotated V-J gene pairs, we found that the relative frequencies of two V-J pairs were different at the occurrence of DCI than at admission, with T cells increasing by over 15%. TCRB CDR3 repertoires may serve as biomarkers to identify severe DCI patients.