Automated classification of infant hip type on ultrasonography using deep learning : preliminary study
Automated classification of infant hip type on ultrasonography using deep learning : preliminary study
复制标题
使用深度学习对婴儿髋关节类型进行超声自动分类：初步研究
DOI：
10.11318/mii.34.92
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
伊賀 敏朗
中科院分区：
文献类型：
--
作者：
李 鎔範;大澤 由瑛;長谷川 晃;皆川 靖子;弦巻 正樹;伊賀 敏朗
本研究的目的是探讨一种方法的有效性，自动分类的婴儿髋关节类型的超声检查。采用卷积神经网络（CNN）对与Graf方法对应的髋关节类型进行自动分类，Graf方法是婴儿髋关节发育不良超声评估的事实上的标准方法。在CNN中，AlexNet被用作神经网络模型。我们收集了49个超声图像进行分类的基础上的格拉夫方法由超声医师。通过旋转、镜像、调整对比度等进行数据扩充，从最初的49张图片中生成了246，960张图片。增强图像被用作CNN的训练数据。10倍交叉验证的准确性为73%。CNN对于婴儿髋关节类型的自动分类将是潜在有效的。
The purpose of this study is to investigate an effectiveness of a method for automatic classification of infant hip types on ultrasonography. A convolutional neural network (CNN) was adopted for the automated classification of hip types corresponding to the Graf method that was defacto standard method for ultrasonographic assessment of infant hip dysplasia. In the CNN, AlexNet was employed as neural network model. We collected 49 ultrasound images that were classified based on the Graf method by an ultrasonographer. Data augmentation by rotating, mirroring, adjusting contrast, etc., generated additional 246,960 images from the original 49 ones. The augmented images were used as training data of the CNN. The accuracy by 10-fold cross validation was 73%. The CNN would be potentially effective for automatic classification of infant hip types.