Réseau d'Imagerie Sud Francilien, Lieusaint, France; Gleamer, Paris, France.
Service de radiologie, Hôpital Avicenne, AP-HP, Paris, France.
Eur J Radiol. 2022 Sep;154:110447. doi: 10.1016/j.ejrad.2022.110447. Epub 2022 Jul 22.
To appraise the performances of an AI trained to detect and localize skeletal lesions and compare them to the routine radiological interpretation.
We retrospectively collected all radiographic examinations with the associated radiologists' reports performed after a traumatic injury of the limbs and pelvis during 3 consecutive months (January to March 2017) in a private imaging group of 14 centers. Each examination was analyzed by an AI (BoneView, Gleamer) and its results were compared to those of the radiologists' reports. In case of discrepancy, the examination was reviewed by a senior skeletal radiologist to settle on the presence of fractures, dislocations, elbow effusions, and focal bone lesions (FBL). The lesion-wise sensitivity of the AI and the radiologists' reports was compared for each lesion type. This study received IRB approval (CRM-2106-177).
A total of 4774 exams were included in the study. Lesion-wise sensitivity was 73.7% for the radiologists' reports vs. 98.1% for the AI (+24.4 points) for fracture detection, 63.3% vs. 89.9% (+26.6 points) for dislocation detection, 84.7% vs. 91.5% (+6.8 points) for elbow effusion detection, and 16.1% vs. 98.1% (+82 points) for FBL detection. The specificity of the radiologists' reports was always 100% whereas AI specificity was 88%, 99.1%, 99.8%, 95.6% for fractures, dislocations, elbow effusions, and FBL respectively. The NPV was measured at 99.5% for fractures, 99.8% for dislocations, and 99.9% for elbow effusions and FBL.
AI has the potential to prevent diagnosis errors by detecting lesions that were initially missed in the radiologists' reports.
评估一款用于检测和定位骨骼病变的人工智能的性能，并将其与常规放射学解释进行比较。
我们回顾性地收集了在 2017 年 1 月至 3 月的 3 个月内，14 个中心的私营影像组中因四肢和骨盆创伤进行的所有放射检查及其相关放射科医生报告。对每个检查进行了人工智能（BoneView，Gleamer）分析，并将其结果与放射科医生报告进行比较。如果存在差异，则由一名高级骨骼放射科医生对检查进行复查，以确定是否存在骨折、脱位、肘部积液和局灶性骨病变（FBL）。比较了人工智能和放射科医生报告对每种病变类型的病变检测灵敏度。本研究获得了 IRB 批准（CRM-2106-177）。
共有 4774 项检查纳入研究。在骨折检测方面，放射科医生报告的病变检测灵敏度为 73.7%，人工智能为 98.1%（+24.4 分）；在脱位检测方面，放射科医生报告的病变检测灵敏度为 63.3%，人工智能为 89.9%（+26.6 分）；在肘部积液检测方面，放射科医生报告的病变检测灵敏度为 84.7%，人工智能为 91.5%（+6.8 分）；在 FBL 检测方面，放射科医生报告的病变检测灵敏度为 16.1%，人工智能为 98.1%（+82 分）。放射科医生报告的特异性始终为 100%，而人工智能的特异性分别为 88%、99.1%、99.8%和 95.6%，用于骨折、脱位、肘部积液和 FBL。在骨折方面，NPV 为 99.5%，在脱位方面为 99.8%，在肘部积液和 FBL 方面为 99.9%。
人工智能有可能通过检测放射科医生报告中最初遗漏的病变来防止诊断错误。
