基于深度卷积神经网络的新生儿髋关节超声图像自动分类:一种结合斑点噪声抑制的新型数据增强方法
本研究基于卷积神经网络构建了髋关节超声图像全自动计算机辅助诊断系统,用于Graf标准切面图像的分类;将图像自动分割为包含必要解剖结构的图像块后输入网络提取特征并分类,数据集分为正常、轻度发育不良和重度发育不良三组;采用优化贝叶斯非局部均值滤波器进行斑点噪声抑制的数据增强后,系统准确率从92.29%提高至97.70%。
要点
- 基于CNN的自动分类系统对Graf标准切面髋关节超声图像进行分类,数据增强后准确率达97.70%。
- 采用优化贝叶斯非局部均值滤波器进行斑点噪声抑制的数据增强,使准确率从92.29%提高至97.70%。
- 自动分割的图像块需包含所有必要解剖结构后输入CNN提取特征并分类。
关键影像表现/征象
- 自动分割的图像块包含所有必要解剖结构后输入CNN以提取判别性特征并分类。
- 采用优化贝叶斯非局部均值滤波器进行斑点噪声抑制的数据增强。
诊断标准与关键数值
- 数据增强后CNN系统准确率为97.70%,数据增强前为92.29%。
临床应用与阅片要点
- 该系统可能帮助评估者提高基于Graf方法诊断发育性髋关节发育不良的精确度。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
Neonatal hip ultrasound imaging has been widely used for a few decades in the diagnosis of developmental dysplasia of the hip (DDH). Graf's method of hip ultrasonography is still the most reproducible because of its classification system; yet, the reproducibility is questionable as a result of the high dependency on the skills of the sonographer and the evaluator. A computer-aided diagnosis system may help evaluators increase their precision in the diagnosis of DDH using Graf's method. This study describes a fully automatic computer-aided diagnosis system for the classification of hip ultrasound images captured in Graf's standard plane based on convolutional neural networks (CNNs). Automatically segmented image patches containing all of the necessary anatomical structures were given to the proposed CNN system to extract discriminative features and classify the recorded hips. For ease of evaluation, the data set was divided into three groups: normal, mild dysplasia and severe dysplasia. This study proposes a different approach to data augmentation using speckle noise reduction with an optimized Bayesian non-local mean filter. Data augmentation with this filter increased the accuracy of the proposed CNN system from 92.29% to 97.70%. This new approach for automatic classification of DDH, classifies dysplastic neonatal hips with a high accuracy rate and might help evaluators to increase their evaluation success.
引用
- Sezer A, Sezer HB. Deep Convolutional Neural Network-Based Automatic Classification of Neonatal Hip Ultrasound Images: A Novel Data Augmentation Approach with Speckle Noise Reduction. Ultrasound Med Biol. 2019. PMID: 31882168. doi:10.1016/j.ultrasmedbio.2019.09.018
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。