A Comparative Study of AI-Based Automated and Manual Postprocessing of Head and Neck CT Angiography: An Independent External Validation with Multi-Vendor and Multi-Center Data

• Published in: Neuroradiology 2024-10, Vol.66 (10), p.1765-1780
• Main Authors: Li, Kunhua, Yang, Yang, Niu, Shengwen, Yang, Yongwei, Tian, Bitong, Huan, Xinyue, Guo, Dajing
• Format: Article
• Language: English
• Subjects: Aneurysm; Aneurysms; Angiography; Artificial intelligence in neuroradiology; Automation; Comparative studies; Computed tomography; Diagnostic systems; Head and neck; Head-Neck-ENT Radiology; Image acquisition; Image quality; Imaging; Medical imaging; Medicine; Medicine & Public Health; Neurology; Neuroradiology; Neurosciences; Neurosurgery; Patients; Performance evaluation; Qualitative analysis; Radiation; Radiation dosage; Radiology; Segments; Stenosis
• ISSN: 0028-3940; 1432-1920; 1432-1920
• DOI: 10.1007/s00234-024-03379-y

Purpose To externally validate the performance of automated postprocessing (AP) on head and neck CT Angiography (CTA) and compare it with manual postprocessing (MP). Methods This retrospective study included head and neck CTA-exams of patients from three tertiary hospitals acquired on CT scanners from five manufacturers. AP was performed by CerebralDoc. The image quality was assessed using Likert scales, and the qualitative and quantitative diagnostic performance of arterial stenosis and aneurysm, postprocessing time, and scanning radiation dose were also evaluated . Results A total of 250 patients were included. Among these, 55 patients exhibited significant stenosis (≥ 50%), and 33 patients had aneurysms, diagnosed using original CTA datasets and corresponding multiplanar reconstructions as the reference. While the scores of the V4 segment and the edge of the M1 segment on volume rendering (VR), as well as the C4 segment on maximum intensity projection (MIP), were significantly lower with AP compared to MP across vendors (all P