[1]胡歆迪,杨鑫,周旭,等.智能化婴儿髋关节发育性不良辅助筛查系统[J].深圳大学学报理工版,2021,38(4):408-417.[doi:10.3724/SP.J.1249.2021.04408]
 HU Xindi,YANG Xin,ZHOU Xu,et al.Intelligent auxiliary screening system for development dysplasia of the hip[J].Journal of Shenzhen University Science and Engineering,2021,38(4):408-417.[doi:10.3724/SP.J.1249.2021.04408]
点击复制

智能化婴儿髋关节发育性不良辅助筛查系统
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第38卷
期数:
2021年第4期
页码:
408-417
栏目:
电子与信息科学
出版日期:
2021-07-10

文章信息/Info

Title:
Intelligent auxiliary screening system for development dysplasia of the hip
文章编号:
202104011
作者:
胡歆迪杨鑫周旭王丽敏梁永栋尚宁倪东顾宁
1) 南京医科大学生物医生工程与信息学院,江苏南京210000;2)深圳大学生物医学工程学院,广东深圳 518060;3)广东省妇幼保健院超声诊断科,广东广州510000
Author(s):
HU Xindi1 YANG Xin2 ZHOU Xu2 WANG Limin3 LIANG Yongdong3 SHANG Ning3 NI Dong2 and G Ning1
1) School of Biomedical Engineering and Information, Nanjing Medical University, Nanjing 210000, Jiangsu Province, P.R.China 2) School of Biomedical Engineering, Shenzhen University, Shenzhen 518060, Guangdong Province, P.R.China 3) Ultrasound Department, Guangdong Women and Children Hospital, Guangzhou 510000, Guangdong Province, P.R.China
关键词:
人工智能髋关节发育性不良标准切面图像分类实例分割计算机辅助诊断深度学习特征提取
Keywords:
artificial intelligence development dysplasia of the hip standard plane image classification instance segmentation computer aided diagnosis deep learning feature extraction
分类号:
R318; TP751
DOI:
10.3724/SP.J.1249.2021.04408
文献标志码:
A
摘要:
髋关节发育性不良(development dysplasia of the hip, DDH)是常见的先天性关节疾病之一.目前临床上常采用Graf法对婴儿进行髋关节超声筛查,以提早发现病情,提高治愈率.该方法高度依赖标准切面的选取和关键解剖结构的识别,对医生的知识和经验要求较高.提出智能化婴儿DDH辅助筛查系统,建立自动化筛查流程,实现自动识别标准切面并测量发育指标α角和β角.标准切面自动识别模块基于少样本单类别分类(few-shot one-class classifier, FOC)的神经网络,通过自监督训练方式学习标准切面的特征信息,预测图像的标准化得分. α角和β角快速测量模块基于快速实例网络(fast instance network, FIN),通过高效的单阶段的网络架构和多任务学习模式,对标准切面实时测量并将结果可视化.分别通过自动识别标准切面和自动测量发育指标两类实验对所建立的辅助筛查系统进行验证.与单类别支持向量机、深度支持向量数据描述网络和Ganomaly网络相比,FOC方法的接受者操作特征曲线下面积达到76.43%,性能最优;与全卷积网络、Unet和deeplab V3相比,采用FIN模块测量的α角和β角的平均绝对误差分别为2.48°和4.38°,推理速度达到33.88帧/s,速度最快且性能最优.实验结果表明,该系统可降低对训练数据量的依赖,有助于提升DDH临床筛查的同质化水平,控制测量质量,提高临床筛查的工作效率.
Abstract:
Development dysplasia of the hip (DDH) is one of the common congenital joint diseases and early ultrasound screening of the hip joint conducive to the cure. The Graf method is often used in the clinical diagnose of DDH. It relies on the selection of standard planes and the identification of key anatomical structures, which requires a high level of knowledge and experience of physicians. This study proposes an intelligent infant DDH auxiliary screening system. It is designed to realize automatic identification of standard planes and measure two indicators, α angle and β angle. The automatic recognition standard plane module is based on a few-shot one-class classifier, which can recognize standard planes from the hip joint ultrasound videos. It learns the features of the standard plane with self-supervised training and predicts the standardized score of the image. The automatic fast measurement module is based on a one-stage instance segmentation network. Through the one-stage architecture and multi-task learning mode, it measures two angles on the standard plane in real-time and visualizes the results. The performance of our system is verified by two types of experiments: automatic identification and measurement. Compared with other one-class classifiers, such as one-class support vector machine, deep support vector data description, and Ganomaly, our method performs best, with the area under the receiver operating characteristic 76.43%. Compared with other common neural networks, such as full convolutional network, Unet and deeplab V3, our method is the fastest and shows the most excellent performance. The average errors in alpha and beta angles are 2.48° and 4.38°, and the inference speedis 33.88 frames/s. Experimental results show that our system can reduce the dependence on the amount of training data, improve the homogeneity level of clinical screening for DDH, control the quality of measurement, and improve the efficiency of clinical screening.

相似文献/References:

[1]潘长城,徐晨,李国.解全局优化问题的差分进化策略[J].深圳大学学报理工版,2008,25(2):211.
 PAN Chang-cheng,XU Chen,and LI Guo.Differential evolutionary strategies for global optimization[J].Journal of Shenzhen University Science and Engineering,2008,25(4):211.
[2]骆剑平,李霞.求解TSP的改进混合蛙跳算法[J].深圳大学学报理工版,2010,27(2):173.
 LUO Jian-ping and LI Xia.Improved shuffled frog leaping algorithm for solving TSP[J].Journal of Shenzhen University Science and Engineering,2010,27(4):173.
[3]蔡良伟,李霞.基于混合蛙跳算法的作业车间调度优化[J].深圳大学学报理工版,2010,27(4):391.
 CAI Liang-wei and LI Xia.Optimization of job shop scheduling based on shuffled frog leaping algorithm[J].Journal of Shenzhen University Science and Engineering,2010,27(4):391.
[4]张重毅,刘彦斌,于繁华,等.CDA市场环境模型进化研究[J].深圳大学学报理工版,2010,27(4):413.
 ZHANG Zhong-yi,LIU Yan-bin,YU Fan-hua,et al.Research on the evolution model of CDA market environment[J].Journal of Shenzhen University Science and Engineering,2010,27(4):413.
[5]姜建国,周佳薇,郑迎春,等.一种双菌群细菌觅食优化算法[J].深圳大学学报理工版,2014,31(1):43.[doi:10.3724/SP.J.1249.2014.01043]
 Jiang Jianguo,Zhou Jiawei,Zheng Yingchun,et al.A double flora bacteria foraging optimization algorithm[J].Journal of Shenzhen University Science and Engineering,2014,31(4):43.[doi:10.3724/SP.J.1249.2014.01043]
[6]蔡良伟,刘思麒,李霞,等.基于蚁群优化的正则表达式分组算法[J].深圳大学学报理工版,2014,31(3):279.[doi:10.3724/SP.J.1249.2014.03279]
 Cai Liangwei,Liu Siqi,Li Xia,et al.Regular expression grouping algorithm based on ant colony optimization[J].Journal of Shenzhen University Science and Engineering,2014,31(4):279.[doi:10.3724/SP.J.1249.2014.03279]
[7]宁剑平,王冰,李洪儒,等.递减步长果蝇优化算法及应用[J].深圳大学学报理工版,2014,31(4):367.[doi:10.3724/SP.J.1249.2014.04367]
 Ning Jianping,Wang Bing,Li Hongru,et al.Research on and application of diminishing step fruit fly optimization algorithm[J].Journal of Shenzhen University Science and Engineering,2014,31(4):367.[doi:10.3724/SP.J.1249.2014.04367]
[8]刘万峰,李霞.车辆路径问题的快速多邻域迭代局部搜索算法[J].深圳大学学报理工版,2015,32(2):196.[doi:10.3724/SP.J.1249.2015.02000]
 Liu Wanfeng,and Li Xia,A fast multi-neighborhood iterated local search algorithm for vehicle routing problem[J].Journal of Shenzhen University Science and Engineering,2015,32(4):196.[doi:10.3724/SP.J.1249.2015.02000]
[9]蔡良伟,程璐,李军,等.基于遗传算法的正则表达式规则分组优化[J].深圳大学学报理工版,2015,32(3):281.[doi:10.3724/SP.J.1249.2015.03281]
 Cai Liangwei,Cheng Lu,Li Jun,et al.Regular expression grouping optimization based on genetic algorithm[J].Journal of Shenzhen University Science and Engineering,2015,32(4):281.[doi:10.3724/SP.J.1249.2015.03281]
[10]王守觉,鲁华祥,陈向东,等.人工神经网络硬件化途径与神经计算机研究[J].深圳大学学报理工版,1997,14(1):8.
 Wang Shoujue,Lu Huaxiang,Chen Xiangdong and Zeng Yujuan.On the Hardware for Artificial Neural Networks and Neurocomputer[J].Journal of Shenzhen University Science and Engineering,1997,14(4):8.

更新日期/Last Update: 2021-07-30