Department of Radiology & Diagnostic Imaging, University of Alberta, 2A2.41 WMC, 8440 - 112 St. NW, Edmonton, AB, Canada.
Biomedical Engineering, Schulich School of Engineering, University of Calgary, Canada.
Semin Arthritis Rheum. 2021 Jun;51(3):623-626. doi: 10.1016/j.semarthrit.2021.03.009. Epub 2021 Mar 17.
Preliminary assessment, via OMERACT filter, of manual and automated MRI hip effusion Volumetric Quantitative Measurement (VQM).
For 358 hips (93 osteoarthritis subjects, bilateral, 2 time points), 2 radiologists performed manual VQM using custom Matlab software. A Mask R-CNN artificial-intelligence (AI) tool was trained to automatically compute joint fluid volumes.
Manual VQM had excellent inter-observer reliability (ICC 0.96). AI predicted hip fluid volumes with ICC 0.86 (status), 0.58 (change) vs. 2 human readers.
Hip joint fluid volumes are reliably assessed by VQM. It is feasible to automate this approach using AI, with promising initial reliability.
通过 OMERACT 筛选器，初步评估手动和自动 MRI 髋关节积液容积定量测量（VQM）。
对于 358 个髋关节（93 名骨关节炎患者，双侧，2 个时间点），2 名放射科医生使用定制的 Matlab 软件进行手动 VQM。一个 Mask R-CNN 人工智能（AI）工具被训练来自动计算关节液体积。
手动 VQM 具有极好的观察者间可靠性（ICC 0.96）。人工智能预测髋关节积液量的 ICC 分别为 0.86（状态）、0.58（变化），与 2 名人类读者相比。
髋关节积液量通过 VQM 可靠地评估。使用 AI 自动执行此方法是可行的，初始可靠性有很大希望。
