A Landmark Estimation and Correction Network for Automated Measurement of Sagittal Spinal Parameters

被引:4
作者
Yang, Guosheng [1 ]
Fu, Xiangling [1 ]
Xu, Nanfang [2 ]
Zhang, Kailai [3 ]
Wu, Ji [3 ]
机构
[1] Beijing Univ Posts & Telecommun, Sch Software Engn, Beijing, Peoples R China
[2] Peking Univ Third Hosp, Beijing, Peoples R China
[3] Tsinghua Univ, Dept Elect Engn, Beijing, Peoples R China
来源
NEURAL INFORMATION PROCESSING, ICONIP 2020, PT IV | 2020年 / 1332卷
基金
中国国家自然科学基金;
关键词
Scoliosis; Convolutional neural network; Lateral X-rays;
D O I
10.1007/978-3-030-63820-7_24
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recently, deep learning for spinal measurement in scoliosis achieved huge success. However, we notice that existing methods suffer low performance on lateral X-rays because of severe occlusion. In this paper, we propose the automated Landmark Estimation and Correction Network (LEC-Net) based on a convolutional neural network (CNN) to estimate landmarks on lateral X-rays. The framework consists of two parts (1) a landmark estimation network (LEN) and (2) a landmark correction network (LCN). The LEN first estimates 68 landmarks of 17 vertebrae (12 thoracic vertebrae and 5 lumbar vertebrae) per image. These landmarks may include some failed points on the area with occlusion. Then the LCN estimates the clinical parameters by considering the spinal curvature described by 68 landmarks as a constraint. Extensive experiment results which test on 240 lateral Xrays demonstrate that our method improves the landmark estimation accuracy and achieves high performance of clinical parameters on Xrays with severe occlusion. Implementation code is available at https://github.com/xiaoyanermiemie/LEN-LCN.
引用
收藏
页码:213 / 221
页数:9
相关论文
共 19 条
[1]   Automatic spine curvature estimation from X-ray images of a mouse model [J].
Al Okashi, Omar ;
Du, Hongbo ;
Al-Assam, Hisham .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2017, 140 :175-184
[2]   Automated Measurement of Lumbar Lordosis on Radiographs Using Machine Learning and Computer Vision [J].
Cho, Brian H. ;
Kaji, Deepak ;
Cheung, Zoe B. ;
Ye, Ivan B. ;
Tang, Ray ;
Ahn, Amy ;
Carrillo, Oscar ;
Schwartz, John T. ;
Valliani, Aly A. ;
Oermann, Eric K. ;
Arvind, Varun ;
Ranti, Daniel ;
Sun, Li ;
Kim, Jun S. ;
Cho, Samuel K. .
GLOBAL SPINE JOURNAL, 2020, 10 (05) :611-618
[3]  
Cobb JR., 1947, AM ACADEMY ORTHOPAED, V5, P261
[4]   Fully automated radiological analysis of spinal disorders and deformities: a deep learning approach [J].
Galbusera, Fabio ;
Niemeyer, Frank ;
Wilke, Hans-Joachim ;
Bassani, Tito ;
Casaroli, Gloria ;
Anania, Carla ;
Costa, Francesco ;
Brayda-Bruno, Marco ;
Sconfienza, Luca Maria .
EUROPEAN SPINE JOURNAL, 2019, 28 (05) :951-960
[5]   Cobb method or Harrison posterior tangent method [J].
Harrison, DE ;
Harrison, DD ;
Cailliet, R ;
Troyanovich, SJ ;
Janik, TJ ;
Holland, B .
SPINE, 2000, 25 (16) :2072-2078
[6]  
He KM, 2017, IEEE I CONF COMP VIS, P2980, DOI [10.1109/TPAMI.2018.2844175, 10.1109/ICCV.2017.322]
[7]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[8]  
Hongbo Wu, 2017, Medical Image Computing and Computer Assisted Intervention MICCAI 2017. 20th International Conference. Proceedings: LNCS 10433, P127, DOI 10.1007/978-3-319-66182-7_15
[9]   Cobb Angle Measurement of Spine from X-Ray Images Using Convolutional Neural Network [J].
Horng, Ming-Huwi ;
Kuok, Chan-Pang ;
Fu, Min-Jun ;
Lin, Chii-Jen ;
Sun, Yung-Nien .
COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2019, 2019
[10]   Epidemiology of adolescent idiopathic scoliosis [J].
Konieczny, Markus Rafael ;
Senyurt, Huesseyin ;
Krauspe, Ruediger .
JOURNAL OF CHILDRENS ORTHOPAEDICS, 2013, 7 (01) :3-9