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

Use of Artificial Intelligence Software to Detect Intracranial Aneurysms: A Comprehensive Stroke Center Experience

OBJECTIVE

To evaluate variability in aneurysm detection and the potential of artificial intelligence (AI) software as a screening tool by comparing conventional computed tomography angiography (CTA) images (standard care) with AI software.

METHODS

Neuroradiologists reviewed 770 CTA images and reported the presence or absence of saccular aneurysms. Subsequently, the images were analyzed by AI software. If the software suspected an aneurysm, it flagged the corresponding image. In cases where there was a mismatch between the radiologist's report and the AI findings, an expert neurosurgeon evaluated CTA images providing a definitive conclusion on the presence or absence of an aneurysm.

RESULTS

AI software flagged 33 cases as potential aneurysms; 16 cases were positively identified as aneurysms by radiologists, and 17 were dismissed. A total of 737 cases were considered negative by AI software, while in the same group, radiologists identified aneurysms in 28 CTA images. Compared with the radiologist's report, AI performance had a sensitivity of 36%, specificity of 97.6%, and negative predictive value of 96.2%. There were 45 mismatch cases between AI and radiologists. AI flagged 17 images as showing an aneurysm that was unreported by radiologists; the expert neurosurgeon confirmed that 7 of the 17 images showed an aneurysm. In 28 images considered negative by AI, radiologists indicated aneurysms; 17 of those confirmed by the neurosurgeon.

CONCLUSIONS

AI has the potential to increase the diagnosis of unruptured intracranial aneurysms. However, it must be used as an adjacent tool within the standard of care due to limited applicability in real-world settings.

Digital Subtraction Angiography of Cerebral Arteries: Influence of Cranial Dimensions on X-ray Tube Performance

(1) Background. Digital subtraction angiography (DSA) is indispensable for diagnosing cerebral aneurysms due to its superior imaging precision. However, optimizing X-ray parameters is crucial for accurate diagnosis, with X-ray tube settings significantly influencing image quality. Understanding the relationship between skull dimensions and X-ray parameters is pivotal for tailoring imaging protocols to individual patients. (2) Methods. A retrospective analysis of DSA data from a single center was conducted, involving 251 patients. Cephalometric measurements and statistical analyses were performed to assess correlations between skull dimensions and X-ray tube parameters (voltage and current). (3) Results. The study revealed significant correlations between skull dimensions and X-ray tube parameters, highlighting the importance of considering individual anatomical variations. Gender-based differences in X-ray parameters were observed, emphasizing the need for personalized imaging protocols. (4) Conclusions. Personalized approaches to DSA imaging, integrating individual anatomical variations and gender-specific differences, are essential for optimizing diagnostic outcomes. While this study provides valuable insights, further research across multiple centers and diverse imaging equipment is warranted to validate these findings.

Plasma levels of CD36 and glutathione as biomarkers for ruptured intracranial aneurysm

Evidence has proved that intracranial aneurysm (IA) formation and rupture might be closely related to inflammatory response and oxidative stress. Our objective was to evaluate the potential of CD36 and glutathione (GSH) as biomarkers for IA. In this study, the enzyme-linked immunosorbent assay was used to measure the plasma levels of CD36 and GSH in 30 IA patients and 30 healthy controls. Then, correlation analysis, receiver operating characteristic (ROC) curve, and logistic regression analysis were performed. The results showed that the plasma level of CD36 in IA patients was significantly higher than that in the control group (P < 0.0001), and plasma GSH was significantly lower compared with that in the control group (P < 0.0001). ROC analysis showed that CD36 and GSH had high sensitivity (90.0 and 96.6%) and specificity (96.6 and 86.6%) for IA diagnosis. The combined sensitivity and specificity achieved were 100 and 100%, respectively. The plasma levels of CD36 and GSH did not show a significant correlation with age, the Glasgow Coma Scale, Hunter-Hess score, aneurysm size, aneurysm height, aneurysm neck, and aspect ratio. The AUC of the logistic regression model based on CD36 and GSH was 0.505. Our results suggested that the combination of plasma CD36 and GSH could serve as potential biomarkers for IA rupture.

Topological Data Analysis and Use of Mapper for Cerebral Aneurysm Rupture Status Discrimination Based on 3-Dimensional Shape Analysis

BACKGROUND AND OBJECTIVES

Topological data analysis (TDA), which identifies patterns in data through simplified topological signatures, has yet to be applied to aneurysm research. We investigate TDA Mapper graphs (Mapper) for aneurysm rupture discrimination.

METHODS

Two hundred sixteen bifurcation aneurysms (90 ruptured) from 3-dimensional rotational angiography were segmented from vasculature and evaluated for 12 size/shape and 18 enhanced radiomics features. Using Mapper, uniformly dense aneurysm models were represented as graph structures and described by graph shape metrics. Mapper dissimilarity scores (MDS) were computed between pairs of aneurysms based on shape metrics. Lower MDS described similar shapes, whereas high MDS represented shapes that do not share common characteristics. Ruptured/unruptured average MDS scores (how "far" an aneurysm is shape-wise to ruptured/unruptured data sets, respectively) were evaluated for each aneurysm. Rupture status discrimination univariate and multivariate statistics were reported for all features.

RESULTS

The average MDS for pairs of ruptured aneurysms were significantly larger compared with unruptured pairs (0.055 ± 0.027 vs 0.039 ± 0.015, P < .0001). Low MDS suggest that, in contrast to ruptured aneurysms, unruptured aneurysms have similar shape characteristics. An MDS threshold value of 0.0417 (area under the curve [AUC] = 0.73, 80% specificity, 60% sensitivity) was identified for rupture status classification. Under this predictive model, MDS scores <0.0417 would identify unruptured status. MDS statistical performance in discriminating rupture status was similar to that of nonsphericity and radiomics Flatness (AUC = 0.73), outperforming other features. Ruptured aneurysms were more elongated ( P < .0001), flatter ( P < .0001), and showed higher nonsphericity ( P < .0001) compared with unruptured. Including MDS in multivariate analysis resulted in AUC = 0.82, outperforming multivariate analysis on size/shape (AUC = 0.76) and enhanced radiomics (AUC = 0.78) alone.

CONCLUSION

A novel application of Mapper TDA was proposed for aneurysm evaluation, with promising results for rupture status classification. Multivariate analysis incorporating Mapper resulted in high accuracy, which is particularly important given that bifurcation aneurysms are challenging to classify morphologically. This proof-of-concept study warrants future investigation into optimizing Mapper functionality for aneurysm research.

Detection of Intracranial Aneurysms Using Multiphase CT Angiography with a Deep Learning Model

RATIONALE AND OBJECTIVES

Determine the effect of a multiphase fusion deep-learning model with automatic phase selection in detection of intracranial aneurysm (IA) from computed tomography angiography (CTA) images.

MATERIALS AND METHODS

CTA images of intracranial arteries from patients at Ningbo First Hospital were retrospectively analyzed. Images were randomly classified as training data, internal validation data, or test data. CTA images from cases examined by digital subtraction angiography (DSA) were examined for independent validation. A deep-learning model was constructed by automatic phase selection of multiphase fusion, and compared to the single-phase algorithm to evaluate algorithm sensitivity.

RESULTS

We analyzed 1110 patients (1493 aneurysms) as training data, 139 patients (174 aneurysms) as internal validation data, and 134 patients (175 aneurysms) as test data. The sensitivity of the multiphase analysis of the internal validation data, test data, and independent validation data were greater than from the single-phase analysis. The recall of the multiphase selection was greater or equal to that of single-phase selection in the aneurysm position, shape, size, and rupture status. Use of the test data to determine the presence and absence of aneurysm rupture led to a recall from multiphase selection of 94.8% and 87.6% respectively; both of these values were greater than those from single-phase selection (89.6% and 79.4%).

CONCLUSION

A multiphase fusion deep learning model with automatic phase selection provided automated detection of IAs with high sensitivity.

Clinical applications of artificial intelligence in radiology

The rapid growth of medical imaging has placed increasing demands on radiologists. In this scenario, artificial intelligence (AI) has become an attractive partner, one that may complement case interpretation and may aid in various non-interpretive aspects of the work in the radiological clinic. In this review, we discuss interpretative and non-interpretative uses of AI in the clinical practice, as well as report on the barriers to AI's adoption in the clinic. We show that AI currently has a modest to moderate penetration in the clinical practice, with many radiologists still being unconvinced of its value and the return on its investment. Moreover, we discuss the radiologists' liabilities regarding the AI decisions, and explain how we currently do not have regulation to guide the implementation of explainable AI or of self-learning algorithms.