Ankle Fracture Detection Utilizing a Convolutional Neural Network Ensemble Implemented with a Small Sample, De Novo Training, and Multiview Incorporation
Ankle Fracture Detection Utilizing a Convolutional Neural Network Ensemble Implemented with a Small Sample, De Novo Training, and Multiview Incorporation
复制标题
DOI：
10.1007/s10278-018-0167-7
复制
发表时间：
2019-08-01
影响因子：
4.4
通讯作者：
Moore, Barry E., II
中科院分区：
文献类型：
--
作者：
Kitamura, Gene;Chung, Chul Y.;Moore, Barry E., II
为了确定能否用小数据集重新训练卷积神经网络(CNN)模型，收集并处理了596例正常和异常踝关节病例。创建了单视图和多视图模型以确定多视图的效果。在训练期间进行数据增强。使用以TensorFlow为框架的Python语言，构建了先发V3、RESNET和XERCEL卷积神经网络。训练是使用单一的X线片进行的。测量的输出指标为准确性、阳性预测值(PPV)、阴性预测值(NPV)、敏感性和特异性。使用一张和三张放射照片对模型输出进行了评估。训练后，由CNN的组合创建合奏。采用投票的方法来合并来自三个视图和模型集成的输出。对于单张X线片，所有5个模型的组合产生的准确率最高，为76%。当使用单个案例的所有三个视图时，所有模型的集成产生了最好的输出指标，准确率为81%。尽管我们的数据集很小，但通过使用模型集成和每个案例的3个视图，我们获得了81%的准确率，这与使用大量预先训练的模型和实现手动特征提取的模型的其他模型的准确率一致。
To determine whether we could train convolutional neural network (CNN) models de novo with a small dataset, a total of 596 normal and abnormal ankle cases were collected and processed. Single- and multiview models were created to determine the effect of multiple views. Data augmentation was performed during training. The Inception V3, Resnet, and Xception convolutional neural networks were constructed utilizing the Python programming language with Tensorflow as the framework. Training was performed using single radiographic views. Measured output metrics were accuracy, positive predictive value (PPV), negative predictive value (NPV), sensitivity, and specificity. Model outputs were evaluated using both one and three radiographic views. Ensembles were created from a combination of CNNs after training. A voting method was implemented to consolidate the output from the three views and model ensemble. For single radiographic views, the ensemble of all 5 models produced the best accuracy at 76%. When all three views for a single case were utilized, the ensemble of all models resulted in the best output metrics with an accuracy of 81%. Despite our small dataset size, by utilizing an ensemble of models and 3 views for each case, we achieved an accuracy of 81%, which was in line with the accuracy of other models using a much higher number of cases with pre-trained models and models which implemented manual feature extraction.