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

Abstract

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

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

“…Radiomics data can be integrated with patients' clinical data to identify biomarkers and correlations in imaging that indicate patient prognosis and lesion status. The workflow of radiomics generally includes: (1) image acquisition (2) dataset creation: typically comprises clinical data and imaging material (3) image preprocessing: generally includes image denoising, normalization, and enhancement (4) delineation of the region of interest (ROI): often done through expert manual annotation (5) extraction of radiomic features: includes texture features, intensity features, etc. (6) feature selection and dimensionality reduction: commonly employed techniques include regression models for supervised learning or clustering models for unsupervised learning (7) model development and validation: typically utilizes machine learning and deep learning methods applied to binary or multi-class tasks, with model predictive results applied to external validation datasets to ensure the model's generalizability.…”

“…Digital subtraction angiography (DSA) is considered the gold standard for IA diagnosis; however, its invasive nature, high risk, and cost limit its clinical application ( 3 , 4 ). With the continuous development of imaging technology, non-invasive methods like CT angiography (CTA) and magnetic resonance angiography (MRA) are increasingly used for IA detection ( 5 ). CTA, known for its non-invasiveness and convenience, has become a primary method for vascular lesion screening, though it does not provide hemodynamic information of aneurysms ( 6 ).…”