[论文解读] A Computer-Aided Diagnosis System Using Artificial Intelligence for Hip Fractures -Multi-Institutional Joint Development Research-

Yoichi Sato, Yasuhiko Takegami+6 more|arXiv (Cornell University)|Mar 11, 2020

Radiomics and Machine Learning in Medical Imaging参考文献 32被引用 5

一句话总结

本研究提出了一种基于深度学习的多中心计算机辅助诊断（CAD）系统，用于在前后位骨盆X光片中检测髋部骨折。该系统使用在4,851名患者共10,484张图像上微调的EfficientNet-B4模型进行训练，取得了96.1%的准确率、95.2%的敏感度、96.9%的特异度以及0.99的AUC，且通过Grad-CAM实现了可解释的诊断依据。

ABSTRACT

[Objective] To develop a Computer-aided diagnosis (CAD) system for plane frontal hip X-rays with a deep learning model trained on a large dataset collected at multiple centers. [Materials and Methods]. We included 5295 cases with neck fracture or trochanteric fracture who were diagnosed and treated by orthopedic surgeons using plane X-rays or computed tomography (CT) or magnetic resonance imaging (MRI) who visited each institution between April 2009 and March 2019 were enrolled. Cases in which both hips were not included in the photographing range, femoral shaft fractures, and periprosthetic fractures were excluded, and 5242 plane frontal pelvic X-rays obtained from 4,851 cases were used for machine learning. These images were divided into 5242 images including the fracture side and 5242 images without the fracture side, and a total of 10484 images were used for machine learning. A deep convolutional neural network approach was used for machine learning. Pytorch 1.3 and Fast.ai 1.0 were used as frameworks, and EfficientNet-B4, which is pre-trained ImageNet model, was used. In the final evaluation, accuracy, sensitivity, specificity, F-value and area under the curve (AUC) were evaluated. Gradient-weighted class activation mapping (Grad-CAM) was used to conceptualize the diagnostic basis of the CAD system. [Results] The diagnostic accuracy of the learning model was accuracy of 96. 1 %, sensitivity of 95.2 %, specificity of 96.9 %, F-value of 0.961, and AUC of 0.99. The cases who were correct for the diagnosis showed generally correct diagnostic basis using Grad-CAM. [Conclusions] The CAD system using deep learning model which we developed was able to diagnose hip fracture in the plane X-ray with the high accuracy, and it was possible to present the decision reason.

研究动机与目标

• 开发一种可靠且可泛化的基于人工智能的髋部骨折计算机辅助诊断（CAD）系统。
• 利用大规模多中心前后位骨盆X光片数据集，训练深度学习模型以提升诊断性能。
• 通过集成Grad-CAM技术，确保诊断过程的透明性，可视化模型的决策过程。
• 使用准确率、敏感度、特异度、F值和AUC等标准指标评估模型性能。
• 通过多中心合作，验证系统在多样化临床环境中的鲁棒性和临床相关性。

提出的方法

• 使用PyTorch 1.3和在ImageNet上预训练的EfficientNet-B4架构，训练了一个深度卷积神经网络（DCNN）。
• 数据集包含来自4,851名患者的5,242张骨折侧和5,242张非骨折侧X光片，数据采集时间跨度为2009年至2019年，来自多个医疗机构。
• 对图像进行预处理和数据增强，以提高模型的泛化能力，并应用排除标准，剔除影像不完整、股骨干骨折或假体周围骨折的病例。
• 使用五项指标评估模型性能：准确率、敏感度、特异度、F1-score和受试者工作特征曲线下面积（AUC）。
• 采用Grad-CAM生成热图，可视化X光片中对模型分类决策最具影响力的区域。
• 在保留的测试集上对最终模型进行验证，以确保其鲁棒性和临床相关性。

实验结果

研究问题

• RQ1 在大规模多中心髋部X光片数据集上训练的深度学习模型，能否实现对髋部骨折的高诊断准确率？
• RQ2 该模型在多样化临床环境和患者群体中的泛化能力如何？
• RQ3 Grad-CAM能否有效突出提示模型诊断决策的解剖区域？
• RQ4 与临床基准相比，该模型在敏感度、特异度和AUC方面的表现如何？
• RQ5 通过可视化技术，模型的决策过程是否具有可解释性且具备临床意义？

主要发现

• CAD系统在测试集上实现了96.1%的诊断准确率，表明其在前后位X光片中对髋部骨折分类具有高度可靠性。
• 模型敏感度达到95.2%，表明其在正确识别髋部骨折患者方面能力出色。
• 特异度达到96.9%，表明在非骨折病例中假阳性率较低。
• F1-score为0.961，反映出精确率与召回率之间的良好平衡。
• 受试者工作特征曲线下面积（AUC）为0.99，表明具有极强的判别能力。
• Grad-CAM可视化结果证实，模型聚焦于临床相关解剖区域，如股骨颈和大转子区域，从而支持可解释性与诊断信任度。