The state-of-the-art methods of the MURA dataset.

Musculoskeletal conditions affect an estimated 1.7 billion people worldwide, causing intense pain and disability. These conditions lead to 30 million emergency room visits yearly, and the numbers are only increasing. However, diagnosing musculoskeletal issues can be challenging, especially in emergencies where quick decisions are necessary. Deep learning (DL) has shown promise in various medical applications. However, previous methods had poor performance and a lack of transparency in detecting shoulder abnormalities on X-ray images due to a lack of training data and better representation of features. This often resulted in overfitting, poor generalisation, and potential bias in decision-making. To address these issues, a new trustworthy DL framework has been proposed to detect shoulder abnormalities (such as fractures, deformities, and arthritis) using X-ray images. The framework consists of two parts: same-domain transfer learning (TL) to mitigate imageNet mismatch and feature fusion to reduce error rates and improve trust in the final result. Same-domain TL involves training pre-trained models on a large number of labelled X-ray images from various body parts and fine-tuning them on the target dataset of shoulder X-ray images. Feature fusion combines the extracted features with seven DL models to train several ML classifiers. The proposed framework achieved an excellent accuracy rate of 99.2%, F1Score of 99.2%, and Cohen’s kappa of 98.5%. Furthermore, the accuracy of the results was validated using three visualisation tools, including gradient-based class activation heat map (Grad CAM), activation visualisation, and locally interpretable model-independent explanations (LIME). The proposed framework outperformed previous DL methods and three orthopaedic surgeons invited to classify the test set, who obtained an average accuracy of 79.1%. The proposed framework has proven effective and robust, improving generalisation and increasing trust in the final results.

据估计，全球约有17亿人群罹患肌肉骨骼疾病（musculoskeletal conditions），此类病症会引发剧烈疼痛与功能残疾，每年造成3000万人次急诊就诊，且这一数据仍在持续增长。然而，肌肉骨骼疾病的诊断颇具挑战，尤其是在需要快速决策的急诊场景中。深度学习（Deep Learning，DL）已在众多医学应用中展现出应用前景，但此前的相关方法在X线影像（X-ray images）上检测肩部异常时，不仅性能欠佳，还缺乏可解释性，这源于训练数据不足以及特征表征能力有限，往往会引发过拟合、泛化能力不足以及决策过程中的潜在偏倚问题。为解决上述痛点，本研究提出了一种全新的可信深度学习框架，可基于X线影像检测肩部异常，包括骨折、畸形与关节炎等病症。该框架包含两大核心模块：一是同域迁移学习（Same-domain Transfer Learning，TL），用于缓解ImageNet数据集不匹配问题；二是特征融合模块，用于降低错误率并提升最终结果的可信度。同域迁移学习的实现流程为：先在大量涵盖不同身体部位的标注X线影像上对预训练模型进行预训练，随后在肩部X线影像的目标数据集上对模型进行微调。特征融合模块则将提取得到的特征与7个深度学习模型相结合，以训练多个机器学习（Machine Learning，ML）分类器。所提框架取得了优异的性能指标：准确率达99.2%，F1分数（F1Score）为99.2%，科恩kappa系数（Cohen’s kappa）为98.5%。此外，本研究通过三类可视化工具对结果的可靠性进行了验证，分别为基于梯度的类激活热力图（Gradient-based Class Activation Heat Map，Grad CAM）、激活可视化工具以及局部可解释模型无关解释（Locally Interpretable Model-agnostic Explanations，LIME）。所提框架的性能不仅优于此前的深度学习方法，还超过了受邀参与测试集分类任务的3名骨科医师，后者的平均准确率仅为79.1%。实验结果表明，所提框架高效且鲁棒性强，能够有效提升模型泛化能力并增强最终结果的可信度。