Development and Validation of Deep Learning Algorithms for Scoliosis Screening Using Back Images

Overview

Journal Commun Biol

Specialty Biology

Date 2019 Nov 1

PMID 31667364

Citations 44

Authors

Junlin Yang

Kai Zhang

Hengwei Fan

Zifang Huang

Yifan Xiang

Jingfan Yang

Lin He

Lei Zhang

Yahan Yang

Ruiyang Li

Yi Zhu

Chuan Chen

Fan Liu

Haoqing Yang

Yaolong Deng

Weiqing Tan

Nali Deng

Xuexiang Yu

Xiaoling Xuan

Xiaofeng Xie

Xiyang Liu

Haotian Lin

Affiliations

Soon will be listed here.

Abstract

Adolescent idiopathic scoliosis is the most common spinal disorder in adolescents with a prevalence of 0.5-5.2% worldwide. The traditional methods for scoliosis screening are easily accessible but require unnecessary referrals and radiography exposure due to their low positive predictive values. The application of deep learning algorithms has the potential to reduce unnecessary referrals and costs in scoliosis screening. Here, we developed and validated deep learning algorithms for automated scoliosis screening using unclothed back images. The accuracies of the algorithms were superior to those of human specialists in detecting scoliosis, detecting cases with a curve ≥20°, and severity grading for both binary classifications and the four-class classification. Our approach can be potentially applied in routine scoliosis screening and periodic follow-ups of pretreatment cases without radiation exposure.

Citing Articles

Intelligent Evaluation Method for Scoliosis at Home Using Back Photos Captured by Mobile Phones.

Li Y, Peng X, Mao Q, Ma M, Huang J, Zhang S Bioengineering (Basel). 2024; 11(11).

PMID: 39593822 PMC: 11592223. DOI: 10.3390/bioengineering11111162.

A New Method for Scoliosis Screening Incorporating Deep Learning With Back Images.

Zhang L, Pei B, Zhang S, Lu D, Xu Y, Huang X Global Spine J. 2024; :21925682241282581.

PMID: 39264983 PMC: 11559750. DOI: 10.1177/21925682241282581.

Conditional generative adversarial network-assisted system for radiation-free evaluation of scoliosis using a single smartphone photograph: a model development and validation study.

He Z, Lu N, Chen Y, Chui E, Liu Z, Qin X EClinicalMedicine. 2024; 75:102779.

PMID: 39252864 PMC: 11381623. DOI: 10.1016/j.eclinm.2024.102779.

Applications of artificial intelligence for adolescent idiopathic scoliosis: mapping the evidence.

Goldman S, Hui A, Choi S, Mbamalu E, Tirabady P, Eleswarapu A Spine Deform. 2024; 12(6):1545-1570.

PMID: 39153073 PMC: 11499369. DOI: 10.1007/s43390-024-00940-w.

Heatmap-Based Active Shape Model for Landmark Detection in Lumbar X-ray Images.

Choi M, Jang J J Imaging Inform Med. 2024; 38(1):291-308.

PMID: 39103566 PMC: 11811376. DOI: 10.1007/s10278-024-01210-x.

References

Weinstein S, Dolan L, Spratt K, Peterson K, Spoonamore M, Ponseti I . Health and function of patients with untreated idiopathic scoliosis: a 50-year natural history study. JAMA. 2003; 289(5):559-67. DOI: 10.1001/jama.289.5.559. View

Lonstein J, Morrissy R . Scoliosis school screening: is it of value?. Orthopedics. 1989; 12(12):1589-93. DOI: 10.3928/0147-7447-19891201-14. View

Ramirez L, Durdle N, Raso V, Hill D . A support vector machines classifier to assess the severity of idiopathic scoliosis from surface topography. IEEE Trans Inf Technol Biomed. 2006; 10(1):84-91. DOI: 10.1109/titb.2005.855526. View

Sarwark J, Davis M . Evolving Recommendations for Scoliosis Screening: A Compelling Need for Further Research. JAMA. 2018; 319(2):127-129. DOI: 10.1001/jama.2017.20190. View

Grivas T, Vasiliadis E, Maziotou C, Savvidou O . The direct cost of "Thriasio" school screening program. Scoliosis. 2007; 2:7. PMC: 1876446. DOI: 10.1186/1748-7161-2-7. View

Ren S, He K, Girshick R, Sun J . Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans Pattern Anal Mach Intell. 2016; 39(6):1137-1149. DOI: 10.1109/TPAMI.2016.2577031. View

Ting D, Yim-Lui Cheung C, Lim G, Wei Tan G, Quang N, Gan A . Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes. JAMA. 2017; 318(22):2211-2223. PMC: 5820739. DOI: 10.1001/jama.2017.18152. View

Gulshan V, Peng L, Coram M, Stumpe M, Wu D, Narayanaswamy A . Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. JAMA. 2016; 316(22):2402-2410. DOI: 10.1001/jama.2016.17216. View

Ronckers C, Land C, Miller J, Stovall M, Lonstein J, Doody M . Cancer mortality among women frequently exposed to radiographic examinations for spinal disorders. Radiat Res. 2010; 174(1):83-90. PMC: 3982592. DOI: 10.1667/RR2022.1. View

10.

Hoffman D, Lonstein J, Morin M, VISSCHER W, Harris 3rd B, Boice Jr J . Breast cancer in women with scoliosis exposed to multiple diagnostic x rays. J Natl Cancer Inst. 1989; 81(17):1307-12. DOI: 10.1093/jnci/81.17.1307. View

11.

Gurovich Y, Hanani Y, Bar O, Nadav G, Fleischer N, Gelbman D . Identifying facial phenotypes of genetic disorders using deep learning. Nat Med. 2019; 25(1):60-64. DOI: 10.1038/s41591-018-0279-0. View

12.

Negrini S, Aulisa A, Aulisa L, Circo A, de Mauroy J, Durmala J . 2011 SOSORT guidelines: Orthopaedic and Rehabilitation treatment of idiopathic scoliosis during growth. Scoliosis. 2012; 7(1):3. PMC: 3292965. DOI: 10.1186/1748-7161-7-3. View

13.

Kather J, Pearson A, Halama N, Jager D, Krause J, Loosen S . Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat Med. 2019; 25(7):1054-1056. PMC: 7423299. DOI: 10.1038/s41591-019-0462-y. View

14.

Luk K, Lee C, Cheung K, Cheng J, Ng B, Lam T . Clinical effectiveness of school screening for adolescent idiopathic scoliosis: a large population-based retrospective cohort study. Spine (Phila Pa 1976). 2010; 35(17):1607-14. DOI: 10.1097/BRS.0b013e3181c7cb8c. View

15.

Hresko M, Schwend R, Hostin R . Early Detection of Scoliosis-What the USPSTF "I" Means for Us. JAMA Pediatr. 2018; 172(3):216-217. DOI: 10.1001/jamapediatrics.2017.5585. View

16.

Weinstein S, Dolan L, Wright J, Dobbs M . Effects of bracing in adolescents with idiopathic scoliosis. N Engl J Med. 2013; 369(16):1512-21. PMC: 3913566. DOI: 10.1056/NEJMoa1307337. View

17.

Liu X, Thometz J, Lyon R, Klein J . Functional classification of patients with idiopathic scoliosis assessed by the Quantec system: a discriminant functional analysis to determine patient curve magnitude. Spine (Phila Pa 1976). 2001; 26(11):1274-8; discussion 1279. DOI: 10.1097/00007632-200106010-00020. View

18.

Wang L, Zhang K, Liu X, Long E, Jiang J, An Y . Comparative analysis of image classification methods for automatic diagnosis of ophthalmic images. Sci Rep. 2017; 7:41545. PMC: 5282520. DOI: 10.1038/srep41545. View

19.

Ajemba P, Durdle N, Hill D, Raso J . Classifying torso deformity in scoliosis using orthogonal maps of the torso. Med Biol Eng Comput. 2007; 45(6):575-84. DOI: 10.1007/s11517-007-0192-z. View

20.

Fong D, Cheung K, Wong Y, Wan Y, Lee C, Lam T . A population-based cohort study of 394,401 children followed for 10 years exhibits sustained effectiveness of scoliosis screening. Spine J. 2015; 15(5):825-33. DOI: 10.1016/j.spinee.2015.01.019. View