Intracranial aneurysm is a critical pathology related to the arterial wall deterioration. This work is an essential aspect of a large scale project aimed at providing clinicians with a non-invasive patient-specific decision support tool regarding the rupture risk assessment. A machine learning algorithm links the aneurysm shape observed and a database of UIA clinical images associated with in vivo wall mechanical properties and rupture characterisation. The database constitution is derived from a device prototype coupled with medical imaging. It provides the mechanical characterisation of the aneurysm from the wall deformation obtained by inverse analysis based on the variation of luminal volume. Before performing in vivo tests of the device on small animals, a numerical model was built to quantify the device’s impact on the aneurysm wall under natural blood flow conditions. As the clinician will never be able to precisely situate the device, several locations were considered. In preparation for the inverse analysis procedure, artery material laws of increasing complexity were studied (linear elastic, hyper elastic Fung-like).Considering all the device locations and material laws, the device induced relative displacements to the Systole peak (worst case scenario with the highest mechanical stimulus linked to the blood flow) ranging from 375 μm to 1.28 mm. The variation of luminal volume associated with the displacements was between 0.95 % and 4.3 % compared to the initial Systole volume of the aneurysm. Significant increase of the relative displacements and volume variations were found with the study of different cardiac cycle moments between the blood flow alone and the device application. For forthcoming animal model studies, Spectral Photon CT Counting, with a minimum spatial resolution of 250 μm, was selected as the clinical imaging technique. Based on this preliminary study, the displacements and associated volume variations (baseline for inverse analyse), should be observable and exploitable.