Cerebral aneurysms are characterized by bulging intracranial arteries and carry a significant risk of rupture, leading to life-threatening subarachnoid hemorrhage (SAH). Current treatment planning methods often rely on manual assessment and detection, which are both strenuous and prone to error. Early detection and characterization of these vascular anomalies are crucial for effective clinical management. This study presents an automated approach using computer vision and morphometric analysis to improve the detection, segmentation, and geometric measurements of cerebral aneurysms from simulated 2D medical images with cerebral vasculature. The methodology involved a skeleton-based tracking system to measure vessel diameters and detect abnormal dilatations indicative of aneurysms. The proposed method achieved a Jaccard index of 91.68%, sensitivity of 98.75%, and specificity of 99.98% for segmentation, along with sensitivity of 96.41% and specificity of 100% for detection. These results demonstrate the method’s robust performance in identifying segmented areas and anatomical regions of interest, underscoring its potential to enhance the accuracy and efficiency of aneurysm evaluation and treatment planning.