scholarly journals Development and validation of deep learning algorithms for scoliosis screening using back images

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Junlin Yang ◽  
Kai Zhang ◽  
Hengwei Fan ◽  
Zifang Huang ◽  
Yifan Xiang ◽  
...  

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.

2018 ◽  
Vol 21 (4) ◽  
pp. 414-420
Author(s):  
Nam Ik Cho ◽  
Chang Ju Hwang ◽  
Ho Yeon Kim ◽  
Jong-Min Baik ◽  
Youn Suk Joo ◽  
...  

OBJECTIVEThe need for scoliosis screening remains controversial. Nationwide school screening for scoliosis has not been performed in South Korea, and there are few studies on the referral patterns of patients suspected of having scoliosis. This study aimed to examine the referral patterns to the largest scoliosis center in South Korea in the absence of a school screening program and to analyze the factors that influence the appropriateness of referral.METHODSThe medical records of patients who visited a single scoliosis center for a spinal deformity evaluation were reviewed. Among 1895 new patients who visited this scoliosis center between April 2014 and March 2016, 1211 with presumed adolescent idiopathic scoliosis were included in the study. Patients were classified into 4 groups according to the referral method: non–health care provider, primary physician, hospital specialist, or school screening program. The appropriateness of referral was labeled as inappropriate, late, or appropriate. In total, 213 of 1211 patients were excluded because they had received treatment at another medical facility; 998 patients were evaluated to determine the appropriateness of referral.RESULTSOf the 998 referrals of new patients with presumed adolescent idiopathic scoliosis, 162 (16.2%) were classified as an inappropriate referral, 272 (27.3%) were classified as a late referral, and 564 (56.5%) were classified as an appropriate referral. Age, sex, Cobb angle of the major curve, and skeletal maturity were identified as statistically significant factors that correlated with the appropriateness of referral. The referral method did not correlate with the appropriateness of referral.CONCLUSIONSUnder the current health care system in South Korea, a substantial number of patients with presumed adolescent idiopathic scoliosis are referred either late or inappropriately to a tertiary medical center. Although patients referred by school screening programs had a significantly lower late referral rate and higher appropriate referral rate than the other 3 groups, the referral method was not a significant factor in terms of the appropriateness of referral.


Author(s):  
Amy Ka Po Cheung ◽  
Charlie Chiu Yi Lau ◽  
Meanne Ching Man Chan ◽  
Kenny Yat Hong Kwan

Abstract Background Little is known about patients’ understanding of adolescent idiopathic scoliosis (AIS). This paper aims to develop and validate the Scoliosis Misconception Scale (SMS) and to explore patients’ level of misconception about AIS. Methods A total of 195 patients who were newly referred with newly diagnosed AIS were recruited to assess their levels of misconception and psychological distress before and after their first consultation with a specialist. The 17-item SMS was administered to assess patients’ level of misconception about AIS and the Kessler Psychological Distress Scale (K10) was used to measure their level of distress. Results According to the Item Response Theory, all items were within the acceptable range from -3.69 to 2.39 for difficulty parameters, which determined the difficulty of the scale, while most of the items were within the acceptable range from 0.11 to 1.54 for the discrimination parameters, which determined the rate at which the probability of endorsing a correct item changes given ability levels. Internal consistency by marginal reliability was 0.66. One-sample t test revealed that participants on average scored 6.79 (SD = 2.12) before the first clinic session and 6.45 (SD = 2.51) after the first clinic session, both significantly higher than 0 [t(75) = 27.86, p < .001; t(75) = 22.43, p < .001]. Conclusions Despite a longstanding clinical model that functions well to treat AIS, most patients still have significant misconceptions about the condition. This highlights the necessity to assess patients’ knowledge level of a medical condition and potential generalisability of misconception–distress link to the forefront across other illnesses.


Spine ◽  
2006 ◽  
Vol 31 (21) ◽  
pp. 2516-2520 ◽  
Author(s):  
Maahir Ul Haque ◽  
Harry L. Shufflebarger ◽  
Michael O’Brien ◽  
Angel Macagno

Author(s):  
Dalila Scaturro ◽  
Alessandro de Sire ◽  
Pietro Terrana ◽  
Claudio Costantino ◽  
Lorenza Lauricella ◽  
...  

BACKGROUND: Adolescent idiopathic scoliosis screening still needs a considerable implementation, particularly throughout a school-based assessment protocol. OBJECTIVE: This study aims to evaluate the effectiveness of clinical examinations currently in use for the diagnosis of adolescent idiopathic scoliosis, through a survey carried out in secondary schools to standardize a screening protocol that could be generalized. METHODS: In their classrooms, the adolescents underwent an idiopathic scoliosis screening through three examinations: Adam’s test, axial trunk rotation (ATR) and plumb line. In case of single positivity to one of the three examinations, a column X-ray examination was recommended. RESULTS: The sensitivity and diagnostic specificity of Adam’s test or ATR were 56.3% and 92.7%, respectively. The positivity to at least one between ATR or plumb line showed that sensitivity was higher than specificity: 91.3% versus 80.8%; the positivity to at least one between Adams’s test or plumb line showed a sensitivity of 95.2% and a specificity of 81.5%. Finally, the positivity to all three examinations showed an increase in specificity (99.7%). CONCLUSIONS: Taken together, our findings show that this school-based screening protocol had a very high specificity in early diagnosis of adolescent idiopathic scoliosis.


Radiology ◽  
2020 ◽  
Vol 295 (1) ◽  
pp. 136-145 ◽  
Author(s):  
Claudio E. von Schacky ◽  
Jae Ho Sohn ◽  
Felix Liu ◽  
Eugene Ozhinsky ◽  
Pia M. Jungmann ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document