Shape Trumps Size: Image-Based Morphological Analysis Reveals That the 3D Shape Discriminates Intracranial Aneurysm Disease Status Better Than Aneurysm Size

Background. To date, it remains difficult for clinicians to reliably assess the disease status of intracranial aneurysms. As an aneurysm's 3D shape is strongly dependent on the underlying formation processes, it is believed that the presence of certain shape features mirrors the disease status of the aneurysm wall. Currently, clinicians associate irregular shape with wall instability. However, no consensus exists about which shape features reliably predict instability. In this study, we present a classification pipeline that seeks to identify shape features that offer the highest predictive power of aneurysm rupture status.Methods. 3D models of aneurysms were extracted from medical imaging data (3D rotational angiographies) using a standardized protocol. For these aneurysm models, we calculated a variety of established representations of the 3D shape: Geometry indices such as undulation, ellipticity and non-sphericity; writhe- and curvature-based metrics; as well as indices based on Zernike moments. Using statistical learning methods, we investigated the association between shape features and aneurysm disease status. This processing pipeline was applied to a clinical dataset of 750 aneurysms registered in the AneuX morpho database. We report here principal statistical performance metrics (such as the area under curve AUC) for morphometric models to discriminate between ruptured and unruptured aneurysms.Results. Non-sphericity index NSI (AUC = 0.80), normalized Zernike energies (AUC = 0.80) and a modified writhe-index (AUC = 0.78) exhibited the strongest association with rupture status. The combination of predictors further improved the predictive performance (without location: AUC = 0.82, with location AUC = 0.87). The anatomical location was a good predictor for rupture status on its own (AUC = 0.78). Different protocols to isolate the aneurysm dome did not affect the prediction performance. We identified problems regarding generalizability if trained models are applied to datasets with different selection biases.Conclusions. Morphology provided a clear indication of the aneurysm disease status, with parameters measuring shape irregularity being better predictors than size. Because rupture rates vary with aneurysm location, predictive models should be compared to a baseline model using only location as predictor.