Department of Radiology, Boston University School of Medicine, 820 Harrison Avenue, FGH Building, 3rd Floor, Boston, MA, 02118, USA.
Department of Radiology, Stony Brook University Renaissance School of Medicine, HSc Level 4, Room 120, Stony Brook, NY, 11794, USA.
Skeletal Radiol. 2022 Nov;51(11):2129-2139. doi: 10.1007/s00256-022-04070-0. Epub 2022 May 6.
We aimed to perform an external validation of an existing commercial AI software program (BoneView™) for the detection of acute appendicular fractures in pediatric patients.
In our retrospective study, anonymized radiographic exams of extremities, with or without fractures, from pediatric patients (aged 2-21) were included. Three hundred exams (150 with fractures and 150 without fractures) were included, comprising 60 exams per body part (hand/wrist, elbow/upper arm, shoulder/clavicle, foot/ankle, leg/knee). The Ground Truth was defined by experienced radiologists. A deep learning algorithm interpreted the radiographs for fracture detection, and its diagnostic performance was compared against the Ground Truth, and receiver operating characteristic analysis was done. Statistical analyses included sensitivity per patient (the proportion of patients for whom all fractures were identified) and sensitivity per fracture (the proportion of fractures identified by the AI among all fractures), specificity per patient, and false-positive rate per patient.
There were 167 boys and 133 girls with a mean age of 10.8 years. For all fractures, sensitivity per patient (average [95% confidence interval]) was 91.3% [85.6, 95.3], specificity per patient was 90.0% [84.0,94.3], sensitivity per fracture was 92.5% [87.0, 96.2], and false-positive rate per patient in patients who had no fracture was 0.11. The patient-wise area under the curve was 0.93 for all fractures. AI diagnostic performance was consistently high across all anatomical locations and different types of fractures except for avulsion fractures (sensitivity per fracture 72.7% [39.0, 94.0]).
The BoneView™ deep learning algorithm provides high overall diagnostic performance for appendicular fracture detection in pediatric patients.
我们旨在对现有的商业人工智能软件程序（BoneView™）进行外部验证，以检测儿科患者的急性四肢骨折。
在我们的回顾性研究中，纳入了来自 2-21 岁儿科患者的四肢有或无骨折的影像学检查。共纳入 300 例检查（150 例有骨折，150 例无骨折），包括 60 例每个身体部位（手/腕、肘/上臂、肩/锁骨、脚/踝、腿/膝）的检查。Ground Truth 由有经验的放射科医生定义。深度学习算法对骨折进行了检测，比较了其诊断性能与 Ground Truth 的差异，并进行了受试者工作特征分析。统计分析包括每位患者的敏感性（所有骨折均被识别的患者比例）和每位骨折的敏感性（人工智能识别的骨折比例）、每位患者的特异性和每位患者的假阳性率。
有 167 名男孩和 133 名女孩，平均年龄为 10.8 岁。对于所有骨折，每位患者的敏感性（平均[95%置信区间]）为 91.3%[85.6,95.3]，每位患者的特异性为 90.0%[84.0,94.3]，每位骨折的敏感性为 92.5%[87.0,96.2]，无骨折患者的假阳性率为 0.11。所有骨折的患者曲线下面积为 0.93。人工智能的诊断性能在所有解剖部位和不同类型的骨折中均较高，除撕脱性骨折外（骨折敏感性为 72.7%[39.0,94.0]）。
BoneView™深度学习算法对儿科患者四肢骨折的检测具有较高的整体诊断性能。
