BCN MedTech, DTIC, Universitat Pompeu Fabra, Barcelona, Spain.
Computer Aided Medical Procedures, Technische Universität München, Munich, Germany.
Int J Comput Assist Radiol Surg. 2020 May;15(5):847-857. doi: 10.1007/s11548-020-02150-x. Epub 2020 Apr 25.
Demonstrate the feasibility of a fully automatic computer-aided diagnosis (CAD) tool, based on deep learning, that localizes and classifies proximal femur fractures on X-ray images according to the AO classification. The proposed framework aims to improve patient treatment planning and provide support for the training of trauma surgeon residents.
A database of 1347 clinical radiographic studies was collected. Radiologists and trauma surgeons annotated all fractures with bounding boxes and provided a classification according to the AO standard. In all experiments, the dataset was split patient-wise in three with the ratio 70%:10%:20% to build the training, validation and test sets, respectively. ResNet-50 and AlexNet architectures were implemented as deep learning classification and localization models, respectively. Accuracy, precision, recall and [Formula: see text]-score were reported as classification metrics. Retrieval of similar cases was evaluated in terms of precision and recall.
The proposed CAD tool for the classification of radiographs into types "A," "B" and "not-fractured" reaches a [Formula: see text]-score of 87% and AUC of 0.95. When classifying fractures versus not-fractured cases it improves up to 94% and 0.98. Prior localization of the fracture results in an improvement with respect to full-image classification. In total, 100% of the predicted centers of the region of interest are contained in the manually provided bounding boxes. The system retrieves on average 9 relevant images (from the same class) out of 10 cases.
Our CAD scheme localizes, detects and further classifies proximal femur fractures achieving results comparable to expert-level and state-of-the-art performance. Our auxiliary localization model was highly accurate predicting the region of interest in the radiograph. We further investigated several strategies of verification for its adoption into the daily clinical routine. A sensitivity analysis of the size of the ROI and image retrieval as a clinical use case were presented.
展示一种基于深度学习的全自动计算机辅助诊断 (CAD) 工具的可行性，该工具可根据 AO 分类对 X 射线图像中的股骨近端骨折进行定位和分类。该框架旨在改善患者的治疗计划，并为创伤外科住院医师的培训提供支持。
收集了 1347 份临床放射学研究的数据库。放射科医生和创伤外科医生使用边界框对所有骨折进行标注，并根据 AO 标准进行分类。在所有实验中，数据集按患者以 70%:10%:20%的比例分为训练集、验证集和测试集。分别实现 ResNet-50 和 AlexNet 架构作为深度学习分类和定位模型。报告准确性、精度、召回率和 F1 分数作为分类指标。根据精度和召回率评估相似病例的检索。
用于将 X 射线图像分类为“A”、“B”和“未骨折”类型的 CAD 工具的 [Formula: see text]-分数达到 87%，AUC 为 0.95。当对骨折与非骨折病例进行分类时，其准确率提高到 94%，AUC 提高到 0.98。骨折的先定位导致与全图像分类相比有所提高。总共，预测的感兴趣区域的中心 100%包含在手动提供的边界框内。系统平均从 10 个病例中检索到 10 个相关图像（来自同一类）。
我们的 CAD 方案对股骨近端骨折进行定位、检测和进一步分类，可达到与专家水平和最先进性能相当的结果。我们的辅助定位模型对 X 射线图像中感兴趣区域的预测非常准确。我们进一步研究了几种验证策略，以将其纳入日常临床常规。提出了 ROI 大小的敏感性分析和图像检索作为临床用例。
