Li Kunhua, Yang Yang, Yang Yongwei, Li Qingrun, Jiao Lanqian, Chen Ting, Guo Dajing
Department of Radiology, the Second Affiliated Hospital of Chongqing Medical University, 400010 Chongqing, PR China.
Department of Radiology, the First Affiliated Hospital of Chongqing Medical and Pharmaceutical College, 400060 Chongqing, PR China.
Diagn Interv Imaging. 2025 Jan;106(1):11-21. doi: 10.1016/j.diii.2024.07.008. Epub 2024 Sep 19.
The purpose of this study was to investigate the added value of artificial intelligence (AI) solutions for the detection of arterial stenosis (AS) on head and neck CT angiography (CTA).
Patients who underwent head and neck CTA examinations at two hospitals were retrospectively included. CTA examinations were randomized into group 1 (without AI-washout-with AI) and group 2 (with AI-washout-without AI), and six readers (two radiology residents, two non-neuroradiologists, and two neuroradiologists) independently interpreted each CTA examination without and with AI solutions. Additionally, reading time was recorded for each patient. Digital subtraction angiography was used as the standard of reference. The diagnostic performance for AS at lesion and patient levels with four AS thresholds (30 %, 50 %, 70 %, and 100 %) was assessed by calculating sensitivity, false-positive lesions index (FPLI), specificity, and accuracy.
A total of 268 patients (169 men, 63.1 %) with a median age of 65 years (first quartile, 57; third quartile, 72; age range: 28-88 years) were included. At the lesion level, AI improved the sensitivity of all readers by 5.2 % for detecting AS ≥ 30 % (P < 0.001). Concurrently, AI reduced the FPLI of all readers and specifically neuroradiologists for detecting non-occlusive AS (all P < 0.05). At the patient level, AI improved the accuracy of all readers by 4.1 % (73.9 % [1189/1608] without AI vs. 78.0 % [1254/1608] with AI) (P < 0.001). Sensitivity for AS ≥ 30 % and the specificity for AS ≥ 70 % increased for all readers with AI assistance (P = 0.01). The median reading time for all readers was reduced from 268 s without AI to 241 s with AI (P< 0.001).
AI-assisted diagnosis improves the performance of radiologists in detecting head and neck AS, and shortens reading time.
本研究旨在探讨人工智能（AI）解决方案对头颈部CT血管造影（CTA）中动脉狭窄（AS）检测的附加价值。
回顾性纳入在两家医院接受头颈部CTA检查的患者。CTA检查被随机分为第1组（无AI-洗脱期-有AI）和第2组（有AI-洗脱期-无AI），六位阅片者（两名放射科住院医师、两名非神经放射科医生和两名神经放射科医生）分别在无AI和有AI解决方案的情况下独立解读每次CTA检查。此外，记录每位患者的阅片时间。数字减影血管造影用作参考标准。通过计算敏感度、假阳性病变指数（FPLI）、特异度和准确度，评估在四个AS阈值（30%、50%、70%和100%）下病变和患者层面AS的诊断性能。
共纳入268例患者（169例男性，占63.1%），中位年龄65岁（第一四分位数，57岁；第三四分位数，72岁；年龄范围：28 - 88岁）。在病变层面，AI在检测AS≥30%时将所有阅片者的敏感度提高了5.2%（P < 0.001）。同时，AI降低了所有阅片者尤其是神经放射科医生检测非闭塞性AS的FPLI（所有P < 0.05）。在患者层面，AI将所有阅片者的准确度提高了4.1%（无AI时为73.9%[1189/1608] vs. 有AI时为78.0%[1254/1608]）（P < 0.001）。在AI辅助下，所有阅片者对AS≥30%的敏感度和对AS≥70%的特异度均有所提高（P = 0.01）。所有阅片者的中位阅片时间从无AI时的268秒减少至有AI时的241秒（P < 0.001）。
AI辅助诊断提高了放射科医生对头颈部AS的检测性能，并缩短了阅片时间。
