Scoliosis is a widespread musculoskeletal disorder of bending and twisting of spine. In this, spine curves to the side and in severe cases it can twist and take several bends. For the diagnosis and treatment of scoliotic patients, the Cobb’s angle is a critical marker of the body’s curvature. Early detection and proper treatment of scoliosis help individuals maintain a higher quality of life. There are many researches that have been conducted to automate the manual measurement of the angle and every investigation has their own limitations.
Approach
This paper presents a method for precisely measuring the Cobb’s angle using deep learning based techniques. Mainly it comprises of feature enhancement of augmented dataset, a bespoke code for landmark estimation on the spine, segmentation model based on the U-Net architecture and a custom code for Cobb’s angle measurement. These measured angles are compared to the given angles for the segmentation on X-ray images.
Results
The proposed technique offers an automated way for precisely measuring this angle with an overall accuracy of and Root Mean Square Error of , which can lower the variability, facilitate early detection, accurate diagnosis, and monitoring of scoliosis progression. Additionally, it aids in the treatment planning and evaluating treatment outcomes.
Conclusion
The combination of deep learning techniques, accurate landmark estimation, and segmentation has enabled to develop an automated system that can consistently and objectively measure the Cobb’s angle with high accuracy. Healthcare professionals can enhance the quality of care and can improve long-term outcomes for individuals with scoliosis using this method.
NegriniSDonzelliSAulisaAG, et al.2016 sosort guidelines: orthopaedic and rehabilitation treatment of idiopathic scoliosis during growth. Scol Spin Disor2018; 13: 1–48.
2.
AsherMABurtonDC. Adolescent idiopathic scoliosis: natural history and long term treatment effects. Scoliosis2006; 1: 1–10.
3.
KhanMNaseerAWaliA, et al.A roman urdu corpus for sentiment analysis. Comput J2024; 67: bxae052.
4.
GormanKFJulienCMoreauA. The genetic epidemiology of idiopathic scoliosis. Eur Spine J2012; 21: 1905–1919.
5.
TamoorMOsamaSYounasI, et al.Comparison of different multi objective evolutionary algorithms for bug localization. In: International conference on advances on applied cognitive computing–ACC, 2018.
6.
TamoorMGulHQaiserH, et al.An optimal formulation of feature weight allocation for cbr using machine learning techniques. In: 2015 SAI Intelligent systems conference (IntelliSys), 2015, pp.61–67. IEEE.
7.
TamoorMNaseerAKhanA, et al.Skin lesion segmentation using an ensemble of different image processing methods. Diagnostics2023; 13: 2684.
8.
TanZYangKSunY, et al.An automatic scoliosis diagnosis and measurement system based on deep learning. In: 2018 IEEE International conference on robotics and biomimetics (ROBIO), 2018, pp.439–443. IEEE.
9.
NawazMAdnanATariqU, et al.Automated career counseling system for students using cbr and j48. J Appl Environ Biol Sci2015; 4: 113–120.
10.
ReamyBVSlakeyJB. Adolescent idiopathic scoliosis: review and current concepts. Am Fam Physician2001; 64: 111–117.
11.
WaliAAhmadMNaseerA, et al.Stynmedgan: medical images augmentation using a new gan model for improved diagnosis of diseases. J Intell Fuzzy Syst2023; 44: 10027–10044.
12.
LonsteinJECarlsonJ. The prediction of curve progression in untreated idiopathic scoliosis during growth. JBJS1984; 66: 1061–1071.
13.
SaleemMATamoorMAsifS. An efficient method for gender classification using hybrid cbr. In: 2016 Future technologies conference (FTC), 2016, pp.116–120. IEEE.
14.
MalikYSTamoorMNaseerA, et al.Applying an adaptive otsu-based initialization algorithm to optimize active contour models for skin lesion segmentation. J Xray Sci Technol2022; 30: 1169–1184.
15.
KukloTRPotterBKPolly JrDW, et al.Reliability analysis for manual adolescent idiopathic scoliosis measurements. Spine2005; 30: 444–454.
16.
NegriniSMinozziSBettany-SaltikovJ, et al.Braces for idiopathic scoliosis in adolescents. Cochra Database Syst Rev2015; 6.
17.
NaultMLMac-ThiongJMRoy-BeaudryM, et al.Three-dimensional spinal morphology can differentiate between progressive and nonprogressive patients with adolescent idiopathic scoliosis at the initial presentation: a prospective study. Spine2014; 39: E601.
DavidsJRChamberlinEBlackhurstDW. Indications for magnetic resonance imaging in presumed adolescent idiopathic scoliosis. JBJS2004; 86: 2187–2195.
20.
LarsonANFletcherNDDanielC, et al.Lumbar curve is stable after selective thoracic fusion for adolescent idiopathic scoliosis: a 20-year follow-up. Spine2012; 37: 833–839.
SunYXingYZhaoZ, et al.Comparison of manual versus automated measurement of cobb angle in idiopathic scoliosis based on a deep learning keypoint detection technology. Eur Spine J2022; 31: 1969–1978.
23.
JinCWangSYangG, et al.A review of the methods on cobb angle measurements for spinal curvature. Sensors2022; 22: 3258.
24.
MaaliwRRSusaJABAlonAS, et al.A deep learning approach for automatic scoliosis cobb angle identification. In: 2022 IEEE World AI IoT congress (AIIoT). pp.111–117. DOI: 10.1109/AIIoT54504.2022.9817290.
25.
DubostFColleryBRenaudierA, et al.Automated estimation of the spinal curvature via spine centerline extraction with ensembles of cascaded neural networks. In: International workshop and challenge on computational methods and clinical applications for spine imaging, 2020, pp.88–94. Springer.
26.
VyasDGanesanAMeelP. Computation and prediction of cobb’s angle using machine learning models. In: 2022 2nd International conference on intelligent technologies (CONIT), 2022, pp.1–6. IEEE.
27.
KhanalBDahalLAdhikariP, et al.Automatic cobb angle detection using vertebra detector and vertebra corners regression. In: International Workshop and challenge on computational methods and clinical applications for spine imaging, 2020, pp.81–87. Springer.
28.
FuXYangGZhangK, et al.An automated estimator for cobb angle measurement using multi-task networks. Neur Comput Appl2021; 33: 4755–4761.
29.
CaesarendraWRahmaniarWMathewJ, et al.Automated cobb angle measurement for adolescent idiopathic scoliosis using convolutional neural network. Diagnostics2022; 12: 396.
30.
WongJReformatMParentE, et al.Convolutional neural network to segment laminae on 3D ultrasound spinal images to assist cobb angle measurement. Ann Biomed Eng2022; 50: 401–412.
31.
CuiJLGaoDDShenSJ. Cobb angle measurement method of scoliosis based on u-net network. Res Square2021. DOI: https://doi.org/10.21203/rs.3.rs-604546/v1
32.
SunHZhenXBaileyC, et al.Direct estimation of spinal cobb angles by structured multi-output regression. In: International conference on information processing in medical imaging, 2017, pp.529–540. Springer.
33.
Garcia-CanoECosíoFADuongL, et al.Prediction of spinal curve progression in adolescent idiopathic scoliosis using random forest regression. Comput Biol Med2018; 103: 34–43.
34.
AlukaevDKiselevSMustafaevT, et al.A deep learning framework for vertebral morphometry and cobb angle measurement with external validation. Eur Spine J2022; 31: 1–10.
35.
MakhdoomiNAGunawanTSIdrisNH, et al.Development of scoliotic spine severity detection using deep learning algorithms. In: 2022 IEEE 12th Annual computing and communication workshop and conference (CCWC), 2022, pp.0574–0579. IEEE.
36.
HuangXLuoMLiuL, et al.The comparison of convolutional neural networks and the manual measurement of cobb angle in adolescent idiopathic scoliosis. Global Spine J2022; 14: 21925682221098672.
37.
WangYHuangLWuM, et al.Multi-input adaptive neural network for automatic detection of cervical vertebral landmarks on x-rays. Comput Biol Med2022; 146: 105576.
38.
MagnideETchahaGWJoncasJ, et al.Automatic bone maturity grading from eos radiographs in adolescent idiopathic scoliosis. Comput Biol Med2021; 136: 104681.
39.
ZhangYYuanLWangY, et al.Sau-net: Efficient 3D spine mri segmentation using inter-slice attention. In: Medical imaging with deep learning, 2020, pp.903–913. PMLR.
40.
WangSJiangZYangH, et al.Automatic segmentation of lumbar spine mri images based on improved attention u-net. Comput Intell Neurosci2022; 2022.
41.
LiHLuoHHuanW, et al.Automatic lumbar spinal mri image segmentation with a multi-scale attention network. Neur Comput Appl2021; 33: 11589–11602.
42.
Maaliw IIIRR. Scolionet: An automated scoliosis cobb angle quantification using enhanced x-ray images and deep learning models. J Imag2023; 9: 265.
43.
HorngMHKuokCPFuMJ, et al.Cobb angle measurement of spine from x-ray images using convolutional neural network. Comput Math Methods Med2019; 2019: 6357171.
ShortenCKhoshgoftaarTM. A survey on image data augmentation for deep learning. J Big Data2019; 6: 1–48.
46.
ChengXHaoYXuJ, et al.Lisnn: Improving spiking neural networks with lateral interactions for robust object recognition. In: IJCAI, 2020, pp.1519–1525. Yokohama.
47.
AlomarKAyselHICaiX. Data augmentation in classification and segmentation: A survey and new strategies. J Imag2023; 9: 46.
48.
GoyalBAgrawalSSohiB. Noise issues prevailing in various types of medical images. Biomed Pharmacol J2018; 11: 1227.
49.
RonnebergerOFischerPBroxT. U-net: Convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention–MICCAI 2015: 18th International conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, 2015, pp.234–241. Springer.
ClevertDAUnterthinerTHochreiterS. Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:151107289 2015.
52.
MilletariFNavabNAhmadiSA. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 fourth international conference on 3D vision (3DV), 2016, pp.565–571. IEEE.
