摘要
目的基于CT图像重建人体颈椎节段的三维模型和3D打印技术,为临床诊断提供清晰、特异的病变模型,提高模拟手术效果。方法采用AlexNet网络作为深度学习模型,并运用迁移学习对该模型进行预置。将训练样本按照椎体部位分为4类并进行标记,并利用数据扩增提高分类准确率。结果扩增后图像分类准确率由94.95%提高到97.72%,测试时间由2.05 s增加到3.03 s。结论利用卷积神经网络对CT图像进行身体定位是可行的,而数据扩增技术在提高分类准确率的同时也增加了训练及测试时间。
Objective To locate CT images by using the deep learning model based on convolutional neural network.Methods The AlexNet network was used as a deep learning model,which was preset by the transfer learning approach.Training samples were divided into 4 categories according to the vertebral body parts and labeled,and the data augmentation was used to improve the classification accuracy.Results The accuracy of image classification after augmentation increased from 94.95%to 97.72%,and the testing time increased from 2.05 s to 3.03 s.Conclusion It is feasible to use the convolutional neural network to locate CT images.The data augmentation approach can increase the classification accuracy but also increase the training and testing time.
作者
余行
蒋家良
何奕松
姜晓璇
傅玉川
YU Hang;JIANG Jialiang;HE Yisong;JIANG Xiaoxuan;FU Yuchuan(Department of Radiotherapy,West China Hospital of Sichuan University,Chengdu,610041)
出处
《中国医疗器械杂志》
2019年第6期454-458,共5页
Chinese Journal of Medical Instrumentation
关键词
卷积神经网络
CT图像定位
深度学习
数据扩增
convolutional neural network
CT image localization
deep learning
data augmentation