[1]WEI Xuanxuan,HUANG Zijian,CAO Le,et al.Scoliosis screening method using lightweight pose estimation network[J].CAAI Transactions on Intelligent Systems,2023,18(5):1039-1046.[doi:10.11992/tis.202203038]
Copy

Scoliosis screening method using lightweight pose estimation network

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 18 Number of periods: 2023 5 Page number: 1039-1046 Column: 学术论文—机器学习 Public date: 2023-09-05
Title:
Scoliosis screening method using lightweight pose estimation network
Author(s):
WEI Xuanxuan1;  HUANG Zijian1;  CAO Le2;  YANG Hao1;  FANG Yu1
1. School of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai 201620, China;
2. School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
Keywords:
scoliosis; pose estimation; lightweight; depooling; deconvolution; heatmap regression; classifier; screening system
CLC:
TP391.4；TP183
DOI:
10.11992/tis.202203038
Abstract:
Scoliosis is an abnormal deformity of the spine, and if left untreated, may eventually lead to severe health problems. X-rays and surface appearance measurements of the human body can be used to screen scoliosis; however, the existing methods pose several limitations, including high cost, low efficiency, and limited suitability for all patients. Herein, a scoliosis screening method is proposed based on a lightweight human pose estimation network. First, using the first 13 layers of MobileNetV3 as the encoder of the lightweight human pose estimation network, the two-dimensional coordinates of coilas can be obtained by coordinate decoding. Second, the coordinates of each coila are used to calculate the spatial features of the human body posture. Finally, scoliosis is graded in detail with three support vector machine binary classifiers, and the trained posture estimation and scoliosis screening models are transplanted into the embedded platform. The experimental results reveal that the system can screen four different degrees of scoliosis, with accuracy rates of 93.0%, 81.7%, 81.3%, and 86.6%. This proposed method provides a convenient solution for scoliosis screening and can be easily disseminated within national health survey work.
References:
[1] 宋艳萍, 姚娜, 沈效平, 等. 功能性训练结合脊柱定点旋转复位法治疗青少年特发性脊柱侧弯的临床研究[J]. 实用医技杂志, 2021, 28(7): 924-926
SONG Yanping, YAO Na, SHEN Xiaoping, et al. Clinical study of functional training combined with spinal fixed-point rotation reduction in the treatment of idiopathic scoliosis in adolescents[J]. Journal of practical medical techniques, 2021, 28(7): 924-926
[2] PINHEIRO A P, COELHO J C, VEIGA A C P, et al. A computerized method for evaluating scoliotic deformities using elliptical pattern recognition in X-ray spine images[J]. Computer methods and programs in biomedicine, 2018, 161: 85-92.
[3] KOTWICKI T, NEGRINI S, GRIVAS T B, et al. Methodology of evaluation of morphology of the spine and the trunk in idiopathic scoliosis and other spinal deformities-6th SOSORT consensus paper[J]. Scoliosis, 2009, 4(1): 1-16.
[4] JIANG Weiwei, ZHOU Guangquan, LAI Kalee, et al. A fast 3-D ultrasound projection imaging method for scoliosis assessment[J]. Mathematical biosciences and engineering, 2019, 16(2): 1067-1081.
[5] KOKABU T, KAWAKAMI N, UNO K, et al. Three-dimensional depth sensor imaging to identify adolescent idiopathic scoliosis: a prospective multicenter cohort study[J]. Scientific reports, 2019, 9: 9678.
[6] YANG Junlin, ZHANG Kai, FAN Hengwei, et al. Development and validation of deep learning algorithms for scoliosis screening using back images[J]. Communications biology, 2019, 2: 390.
[7] 周燕, 刘紫琴, 曾凡智, 等. 深度学习的二维人体姿态估计综述[J]. 计算机科学与探索, 2021, 15(4): 641-657
ZHOU Yan, LIU Ziqin, ZENG Fanzhi, et al. Survey on two-dimensional human pose estimation of deep learning[J]. Journal of frontiers of computer science and technology, 2021, 15(4): 641-657
[8] WEI Shihen, RAMAKRISHNA V, KANADE T, et al. Convolutional pose machines[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 4724?4732.
[9] SUN Ke, XIAO Bin, LIU Dong, et al. Deep high-resolution representation learning for human pose estimation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2020: 5686?5696.
[10] NEWELL A, YANG Kaiyu, DENG Jia. Stacked hourglass networks for human pose estimation[C]//European Conference on Computer Vision. Cham: Springer, 2016: 483?499.
[11] ZHAO Lin, WANG Nannan, GONG Chen, et al. Estimating human pose efficiently by parallel pyramid networks[J]. IEEE transactions on image processing, 2021, 30: 6785-6800.
[12] ZHAO Lin, XU Jie, GONG Chen, et al. Learning to acquire the quality of human pose estimation[J]. IEEE transactions on circuits and systems for video technology, 2021, 31(4): 1555-1568.
[13] OSOKIN D. Real-time 2D multi-person pose estimation on CPU: lightweight OpenPose[EB/OL]. (2018?11?29)[2022?03?21].https://arxiv.org/abs/1811.12004.
[14] LUO Youtao, GAO Xiaoming. Lightweight human pose estimation based on self-attention mechanism[J]. Advances in engineering technology research, 2023, 4(1): 253-253.
[15] REN Haopan, WANG Wenming, ZHANG Kaixiang, et al. Fast and lightweight human pose estimation[J]. IEEE access, 2021, 9: 49576-49589.
[16] BAZAREVSKY V, GRISHCHENKO I, RAVEENDRAN K, et al. BlazePose: on-device real-time body pose tracking[EB/OL]. (2020?06?17)[2022?03?21]. https://arxiv.org/abs/2006.10204.
[17] HOWARD A, SANDLER M, CHEN Bo, et al. Searching for MobileNetV3[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2020: 1314-1324.
[18] 渠涵冰, 贾振堂. 轻量级高分辨率人体姿态估计研究[J]. 激光与光电子学进展, 2022, 59(18): 119-126
QU Hanbing, JIA Zhentang. Lightweight and high-resolution human pose estimation method[J]. Laser & optoelectronics progress, 2022, 59(18): 119-126
[19] 马甜甜, 杨长春, 严鑫杰, 等. 融合知识图谱和轻量级图卷积网络推荐系统的研究[J]. 智能系统学报, 2022, 17(4): 721-727
MA Tiantian, YANG Changchun, YAN Xinjie, et al. Research on the fusion of knowledge graph and lightweight graph convolutional network recommendation system[J]. CAAI transactions on intelligent systems, 2022, 17(4): 721-727
[20] 白健鹏, 王巍, 陈雨溪, 等. 基于轻量型YOLOv5的风机桨叶检测与空间定位[J]. 智能系统学报, 2022, 17(6): 1173-1181
BAI Jianpeng, WANG Wei, CHEN Yuxi, et al. Detection and spatial location of wind turbine blades based on lightweight YOLOv5[J]. CAAI transactions on intelligent systems, 2022, 17(6): 1173-1181
[21] RAMIREZ L, DURDLE N G, RASO V J, et al. A support vector machines classifier to assess the severity of idiopathic scoliosis from surface topography[J]. IEEE transactions on information technology in biomedicine, 2006, 10(1): 84-91.
[22] SEOUD L, ADANKON M M, LABELLE H, et al. Prediction of scoliosis curve type based on the analysis of trunk surface topography[C]//2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro. Rotterdam: IEEE, 2010: 408?411.
[23] SUN Haoliang, ZHEN Xiantong, BAILEY C, et al. Direct estimation of spinal Cobb angles by structured multi-output regression[C]//International Conference on Information Processing in Medical Imaging. Cham: Springer, 2017: 529?540.
[24] ZHANG Junhua, LI Hongjian, LV Liang, et al. Computer-aided Cobb measurement based on automatic detection of vertebral slopes using deep neural network[J]. International journal of biomedical imaging, 2017, 2017: 1-6.
[25] WANG Liansheng, XU Qiuhao, LEUNG S, et al. Accurate automated Cobb angles estimation using multi-view extrapolation net[J]. Medical image analysis, 2019, 58: 101542.
[26] PAN Yaling, CHEN Qiaoran, CHEN Tongtong, et al. Evaluation of a computer-aided method for measuring the Cobb angle on chest X-rays[J]. European spine journal, 2019, 28(12): 3035-3043.
[27] TAN Zhiqiang, YANG Kai, SUN Yu, et al. An automatic scoliosis diagnosis and measurement system based on deep learning[C]//2018 IEEE International Conference on Robotics and Biomimetics. Kuala Lumpur: IEEE, 2019: 439?443.
[28] TAN Z Q. Algorithmic study of Lenke classification of idiopa-thic scoliosis based on U-net[M]. Shenzhen: University of Chinese Academy of Sciences ( Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences), 2019.
[29] EICHNER M, FERRARI V, ZURICH S. Better appearance models for pictorial structures[C]//Proc British Machine Vision Conference, London, 2009: 5.
[30] 中华人民共和国国家卫生和计划生育委员会. 中国标准书号: GB/T16133-2014, 儿童青少年脊柱弯曲异常的筛查[S]. 北京: 中国标准出版社, 2014.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems