A comparative study on keypoint detection for developmental dysplasia of hip diagnosis using deep learning models in X-ray and ultrasound images

Sung-Hyun Kim; Kyungsu Lee; Si-Wook Lee; Jin Ho Chang; Jae Youn Hwang; Jihun Kim

doi:10.7776/ASK.2023.42.5.460

All Issue

2023 Vol.42, Issue 5 Preview Page Next Page

Research Article

A comparative study on keypoint detection for developmental dysplasia of hip diagnosis using deep learning models in X-ray and ultrasound images X-ray 및 초음파 영상을 활용한 고관절 이형성증 진단을 위한 특징점 검출 딥러닝 모델 비교 연구

30 September 2023. pp. 460-468

PDF XML

Abstract

Developmental Dysplasia of the Hip (DDH) is a pathological condition commonly occurring during the growth phase of infants. It acts as one of the factors that can disrupt an infant's growth and trigger potential complications. Therefore, it is critically important to detect and treat this condition early. The traditional diagnostic methods for DDH involve palpation techniques and diagnosis methods based on the detection of keypoints in the hip joint using X-ray or ultrasound imaging. However, there exist limitations in objectivity and productivity during keypoint detection in the hip joint. This study proposes a deep learning model-based keypoint detection method using X-ray and ultrasound imaging and analyzes the performance of keypoint detection using various deep learning models. Additionally, the study introduces and evaluates various data augmentation techniques to compensate the lack of medical data. This research demonstrated the highest keypoint detection performance when applying the residual network 152 (ResNet152) model with simple & complex augmentation techniques, with average Object Keypoint Similarity (OKS) of approximately 95.33 % and 81.21 % in X-ray and ultrasound images, respectively. These results demonstrate that the application of deep learning models to ultrasound and X-ray images to detect the keypoints in the hip joint could enhance the objectivity and productivity in DDH diagnosis.

Keywords

Developmental Dysplasia of Hip (DDH)

Ultrasound

X-ray

Deep-learning

Keypoint detection

고관절 이형성증(Developmental Dysplasia of Hip, DDH)은 영유아 성장기에 흔히 발생하는 병리학적 상태로, 영유아의 성장을 방해하고 잠재적인 합병증을 유발하는 원인 중 하나이며 이를 조기에 발견하고 치료하는 것은 매우 중요하다. 기존의 DDH 진단 방법으로는 촉진법과 X-ray 또는 초음파 영상 기반 고관절에서의 특징점 검출을 이용한 진단 방법이 있지만 특징점 검출 시 객관성과 생산성에 제한점이 존재한다. 본 연구에서는 X-ray 및 초음파 영상을 이용한 딥러닝 모델 기반 특징점 검출 방법을 제시하고, 다양한 딥러닝 모델을 이용하여 특징점 검출의 성능을 비교 분석하였다. 또한, 부족한 의료 데이터를 보완하는 방법인 다양한 데이터 증강 기법을 제시하고 비교 평가하였다. 본 연구에서는 Residual Network 152(ResNet152) 및 Simple & Complex augmentation 기법을 적용하였을 때 가장 높은 특징점 검출 성능을 보여주었으며, X-ray 영상에서 평균 Object Keypoint Similarity(OKS)가 약 95.33 %, 초음파 영상에서는 약 81.21 %로 각각 측정되었다. 이러한 결과는 고관절 초음파 및 X-ray 영상에서 딥러닝 모델을 적용함으로써 DDH 진단 시 특징점 검출에 관한 객관성과 생산성을 향상시킬 수 있음을 보여준다.

키워드

영유아 고관절 이형성증

초음파

X-ray

딥러닝

특징점 검출

References

P. Kotlarsky, R. Haber, V. Bialik, and M. Eidelman, "Developmental dysplasia of the hip: What has changed in the last 20 years?," World J. Orthop. 6, 886-901 (2015). 10.5312/wjo.v6.i11.88626716085PMC4686436

Committee on Quality Improvement, Subcommittee on Developmental Dysplasia of the Hip, "Clinical practice guideline: early detection of developmental dysplasia of the hip. committee on quality improvement, subcommittee on developmental dysplasia of the hip. american academy of pediatrics," Pediatrics, 105, 896-905 (2000). 10.1542/peds.105.4.89610742345

M. G. Vitale and D. L. Skaggs, "Developmental dysplasia of the hip from six months to four years of age," J. Am. Acad. Orthop. Surg. 9, 401-411 (2001). 10.5435/00124635-200111000-0000511730331

B. U. Nwachukwu, E. D. McFeely, A. Y. Nasreddine, J. A. Krcik, J. Frank, and M. S. Kocher, "Complications of hip arthroscopy in children and adolescents," J. Pediatr. Orthop. 31, 227-231 (2011). 10.1097/BPO.0b013e31820cadc521415679

T. G. Barlow, "Early diagnosis and treatment of congenital dislocation of the hip," Proc. R. Soc. Med. 56, 804-806 (1963). 10.1177/003591576305600920

J. E. Andersson and P. O. Funnemark, "Neonatal hip instability: screening with anterior-dynamic ultrasound method," J. Pediatr. Orthop. 15, 322-324 (1995). 10.1097/01241398-199505000-000127790488

H. Dogruel, H. Atalar, O. Y. Yavuz, and U. Sayli, "Clinical examination versus ultrasonography in detecting developmental dysplasia of the hip," Int. Orthop. 32, 415-419 (2008). 10.1007/s00264-007-0333-x17333184PMC2323411

R. W. Paton, K. Hinduja, and C. D. Thomas, "The significance of at-risk factors in ultrasound surveillance of developmental dysplasia of the hip. A ten-year prospective study," J. Bone Joint Surg. Br. 87, 1264-1266 (2005). 10.1302/0301-620X.87B9.1656516129755

K. R. Price, R. Dove, and J. B. Hunter, "The use of X-ray at 5 months in a selective screening programme for developmental dysplasia of the hip," J. Child Orthop. 5, 195-200 (2011). 10.1007/s11832-011-0338-222654980PMC3100463

C. Geng, H. Xu, Xi. Zhan, L. Li, Q. Song, L. Zhang, and L. Ge, "Using 3-dimensional ultrasound islice technology for the diagnosis of developmental dysplasia of the hip," J. Ultrasound Med. 39, 1117-1123 (2020). 10.1002/jum.1519331814148PMC7318168

J. Li, B. Zhao, H. Ji, and W. Ding, "Application value of combined diagnosis of ultrasound, MRI, and X-Ray in developmental dysplasia of the hip in children," Contrast Media Mol. Imaging, 2022, 1-6 (2022). 10.1155/2022/163259035115901PMC8791747

D. Williams, E. Protopapa, K. Stohr, J. B. Hunter, and A. Roposch, "The most relevant diagnostic criteria for developmental dysplasia of the hip: a study of British specialists," BMC Musculoskelet Disord. 17, 1-5 (2016). 10.1186/s12891-016-0867-426787538PMC4719727

B. de Castro Paixão Jacobino, M. D. Galvão, A. F. da Silva, and C. C. de Castrob, "Using the Graf method of ultrasound examination to classify hip dysplasia in neonates," Autops. Case Rep. 2, 5-10 (2012). 10.4322/acr.2012.01831528565PMC6735551

T. Trzcinski, M. Christoudias, P. Fua, and V. Lepetit, "Boosting binary keypoint descriptors," Proc. IEEE Conf. CVPR, 2874-2881 (2013). 10.1109/CVPR.2013.370

S. Leutenegger, M. Chli, and R. Y. Siegwart, "BRISK: Binary Robust invariant scalable keypoints," Proc. IEEE Conf. CVPR, 2548-2555 (2011). 10.1109/ICCV.2011.6126542

H. Law and J. Deng, "CornerNet: Detecting Objects as Paired Keypoints," arXiv:1808.01244 (2019). 10.1007/s11263-019-01204-1

M. Fraiwan, N. Al-Kofahi, O. Hanatleh, and A. ibnian, "A dataset of DDH x-ray images," Mendeley Data (2022).

K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," IEEE Conf. Computer Vision and Pattern Recognition, 770-778 (2016). 10.1109/CVPR.2016.9026180094

H. H. Pham, H. Salmane, L. Khoudour, A. Crouzil, P. Zegers, and S. A. Velastin, "A unified deep framework for joint 3D pose estimation and action recognition from a single RGB camera," arXiv:1907.06968 (2019). 10.3390/s2007182532218350PMC7180926

A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," Neural Information Processing Systems, 141, 1097-1105 (2012).

K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv: 1409.1556 (2014).

J. G. Moreno-Torres, J. A. Saez, and F. Herrera, "Study on the impact of partition-induced dataset shift on k-fold cross-validation," IEEE Trans. Neural Netw. Learn. Syst. 23, 1304-1312 (2012). 10.1109/TNNLS.2012.219951624807526

G. Liu, K. J. Shih, T. -C. Wang, F. A. Reda, K. Sapra, Z. Yu, A. Tao, and B. Catanzaro, "Partial convolution based padding," arXiv:1811.11718 (2018).

L. Huang, W. Pan, Y. Zhang, L. Qian, N. Gao, and Y. Wu, "Data augmentation for deep learning-based radio modulation classification," IEEE Access, 8, 1498-1506 (2019). 10.1109/ACCESS.2019.2960775

J. Nalepa, M. Marcinkiewicz, and M. Kawulok, "Data augmentation for brain-tumor segmentation: A review," Front. Comput. Neurosci. 13, 1-18 (2019). 10.3389/fncom.2019.0008331920608PMC6917660

L. Nanni, M. Paci, S. Brahnam, and A. Lumini, "Comparison of different image data augmentation approaches," J. Imaging, 7, 254 (2021). 10.3390/jimaging712025434940721PMC8707550

D. Maji, S. Nagori, M. Mathew, and D. Poddar, "YOLO-Pose: Enhancing YOLO for multi person pose estimation using object keypoint similarity loss," arXiv:2204.06806 (2022). 10.1109/CVPRW56347.2022.00297

J. G. Abbott and F. L.Thurstone, "Acoustic speckle: Theory and experimental analysis," Ultrasonic Imaging, 1, 303-324 (1979). 10.1177/016173467900100402575829

C. B. Burckhardt, "Speckle in ultrasound B-mode scans," IEEE Trans. Sonics and Ultrason. 25, 1-6 (1978). 10.1109/T-SU.1978.30978

T. Loupas, W. N. McDicken, and P. L. Allan, "An adaptive weighted median filter for speckle suppression in medical ultrasonic images," IEEE Trans. Circuits and Syst. 36, 129-135 (1989). 10.1109/31.16577

J. L.Jaremko, A. Hareendranathan, S. E. S. Bolouri, R. F. Frey, S. Dulai, and A. L. Bailey, "AI aided workflow for hip dysplasia screening using ultrasound in primary care clinics," Sci. Rep. 13, 9224-9229 (2023). 10.1038/s41598-023-35603-937286559PMC10247760

Information

Publisher :The Acoustical Society of Korea
Publisher(Ko) :한국음향학회
Journal Title :The Journal of the Acoustical Society of Korea
Journal Title(Ko) :한국음향학회지
Volume : 42
No :5
Pages :460-468
Received Date : 2023-06-30
Accepted Date : 2023-09-19
DOI :https://doi.org/10.7776/ASK.2023.42.5.460

The Journal of the Acoustical Society of KoreaISSN:1225-4428(Print) 2287-3775(Online)한국음향학회

All Issue