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.

Keywords: CTA; PRISMA; QUADAS-2; aneurysm detection; computed tomography angiography; evaluation guidelines; false positives per image; healthy controls; meta-analysis; sensitivity; specificity.

Figure A1

Graphical results QUADAS-2 analysis.

Figure 1

Flow diagram for systematic review and meta-analysis of cerebral aneurysm detection using artificial intelligence.

Figure 2

Forest plot of pooled lesion-level IA detection sensitivity from papers [8,9,19,20,21,22,23,24,25,26,27,28,29,30]. The 95% confidence intervals (CIs) are given in square brackets. If CIs were not given in the original study, we reported herein the point estimates of the pooled lesion-level sensitivity.

Figure 3

Lesion-level sensitivity with respect to the IA size category (noted on top) [8,17,20,21,23,24,27,29]. * means no exact number of cases per size reported; approximations derived from Figure 3 in Bo et al. paper [24]. ^‡ means authors used external validation but reported size-based performance on internal dataset.

Figure 4

Enhanced FROC with lesion-level sensitivity on the vertical axis versus the number of False Positives (FPs) per image on the horizontal axis. Each data point represents the result from one study [8,9,19,20,21,22,23,24,25,26,27,28,29], whereas its color represents the number of test images, and size indicates the average IA size.