互联网众包图像能否用于训练可泛化的关节脱位深度学习算法
研究从在线放射学仓库收集肩、肘、髋及全髋关节置换四个关节各100张X线片(50脱位、50未脱位)训练卷积神经网络分类器,并在三家医院各100张外部测试集上评估;最佳模型外部AUROC分别为肘1.0/0.998、髋0.993/0.880、肩1.0/0.993、全髋关节置换1.0/0.950,热力图显示模型关注关节区域。
要点
- 肘、肩、全髋关节置换脱位CNN外部测试AUROC均≥0.950,髋关节为0.880。
- 类激活热力图显示模型对脱位与未脱位关节均关注关节区域。
- 作者认为在线仓库可作为关节脱位CNN训练数据的可行来源。
核心结论
- 使用适量互联网X线图像可训练出对关节脱位具有临床泛化能力的卷积神经网络,在线仓库可能是CNN训练数据的可行来源。
研究设计与样本
- 研究论文;从在线放射学仓库收集肩、肘、髋及全髋关节置换四个关节各100张X线片(50脱位、50未脱位),使用实时与静态数据增强训练多种CNN二分类器,最佳分类器在来自三家医院的各100张对应X线片(50脱位)外部测试集上评估,以AUROC评价性能。
诊断标准与关键数值
- 最佳CNN的内部/外部测试集AUROC:肘关节1.0/0.998,髋关节0.993/0.880,肩关节1.0/0.993,全髋关节置换1.0/0.950;类激活热力图显示模型对未脱位与脱位关节均适当关注关节区域。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: Deep learning has the potential to automatically triage orthopedic emergencies, such as joint dislocations. However, due to the rarity of these injuries, collecting large numbers of images to train algorithms may be infeasible for many centers. We evaluated if the Internet could be used as a source of images to train convolutional neural networks (CNNs) for joint dislocations that would generalize well to real-world clinical cases.
METHODS: We collected datasets from online radiology repositories of 100 radiographs each (50 dislocated, 50 located) for four joints: native shoulder, elbow, hip, and total hip arthroplasty (THA). We trained a variety of CNN binary classifiers using both on-the-fly and static data augmentation to identify the various joint dislocations. The best-performing classifier for each joint was evaluated on an external test set of 100 corresponding radiographs (50 dislocations) from three hospitals. CNN performance was evaluated using area under the ROC curve (AUROC). To determine areas emphasized by the CNN for decision-making, class activation map (CAM) heatmaps were generated for test images.
RESULTS: The best-performing CNNs for elbow, hip, shoulder, and THA dislocation achieved high AUROCs on both internal and external test sets (internal/external AUC): elbow (1.0/0.998), hip (0.993/0.880), shoulder (1.0/0.993), THA (1.0/0.950). Heatmaps demonstrated appropriate emphasis of joints for both located and dislocated joints.
CONCLUSION: With modest numbers of images, radiographs from the Internet can be used to train clinically-generalizable CNNs for joint dislocations. Given the rarity of joint dislocations at many centers, online repositories may be a viable source for CNN-training data.
引用
- Wei, Li, Sing, et al. Can images crowdsourced from the internet be used to train generalizable joint dislocation deep learning algorithms? Skeletal Radiol. 2022. PMID: 35624310. doi:10.1007/s00256-022-04077-7
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。