BACKGROUND: Vessel centerline extraction assists in the quantitative analysis of plaque. Current algorithms generate significant errors for tortuous vessels, leading to inaccurate centerline extraction. This study proposed a key point detection algorithm to assist in vessel centerline extraction for the further quantitative analysis of plaque. METHODS: A total of 539 patients with cerebrovascular disease from multiple centers were enrolled in this retrospective study. All the patients underwent 3.0-T magnetic resonance imaging (MRI) scans. Based on the experimental experience of radiologists and clinical requirements, 32 key points were chosen, including the carotid siphon, tiny vessels, and vessel bifurcations. Accurate point detection can improve the accuracy of centerline detection. The evaluation indices included the number of undetected points (undetected_num), the number of erroneously detected points (errodetected_num), and the accuracy of each point (pointacc). The average centerline distance (ACD) was used to evaluate the improvement in centerline extraction. RESULTS: The average accuracy of the algorithm in detecting of the 32 points was 88.99%, and the algorithm had an accuracy exceeding 90% for 18 of these points. The accuracy of the algorithm at the sharp bend of the carotid siphon section reached 97%. The accuracy of the algorithm in detecting the points in the internal carotid artery and middle cerebral artery was 95.4%. Using the key point detection algorithm, the ACD for the right carotid artery was reduced to 0.484±0.321 mm but was 0.529±0.334 mm without the key point detection algorithm. The time required to detect the 32 key points was reduced from 319.843±6.434 to 2.046±0.315 seconds when the algorithm was used. CONCLUSIONS: The proposed algorithm was able to automatically and accurately detect the 32 key points, especially those in the internal carotid artery and middle cerebral artery, improving vessel centerline extraction accuracy, and thus assisting in plaque assessment.