Intracranial aneurysms, which are induced by the weakening of the walls of the brain's blood vessels, are highly risky as they may rupture and cause potentially life-threatening outcomes. To prevent disastrous outcomes, the aneurysms need to be detected in a timely and accurate manner. Conventional detection methods relying on human interpretation of CT scans, however, require a significant amount of time and are prone to errors.pointing to the need for a more automated and dependable approach. Here, we present a Deep Learning based algorithm utilizing CT scan data to predict a variety of intracranial aneurysm types and determine their severity. Aneurysms of four types: dissecting, fusiform, mycotic, and saccular are properly identified by the model, and their severity level is also predicted as Low, Medium, or High Risk. In addition, it enables faster and more accurate clinical decision-making by generating appropriate outcomes and safety protocols for all aneurysm types and levels of severity. By seamlessly incorporating into clinical processes, this technology can potentially enhance the overall level of patient care, lower the demand for invasive interventions, and enhance diagnostic results.