Gelişimsel Kalça Displazisinde Ultrason Görüntülemenin Yapay Zeka ile Değerlendirilmesi

Öz

Amaç: Gelişimsel kalça displazisi, bebeklik döneminde ortaya çıkan yaygın bir hastalıktır. Makine öğreniminin (yapay zeka, AI) tıp alanına girmesi ile hastalıkların erken tanısını ve tedavi başarısını önemli oranda artırmaktadır. Bu çalışma, makine öğrenme tekniklerini (yapay zeka) kullanarak gelişimsel kalça displazisi tarama programında kullanılan ultrason videolarından ultrason görüntüsünün doğruluğunun belirlenmesi amaçlamaktadır. Gereç ve Yöntem: Çalışma, Lokal İkili Model (LBP) metodolojisi aracılığıyla ultrason görüntü özelliklerinin çıkarılmasını içeriyordu. Daha sonra, ‘Decision Tree (DT), Random Forest (RF), K-Nearest Neighbour (KNN), Gradient Boosting (GB), Support Vector Machines (SVM), Naïve Bayes (NB), Linear Regression (LR), and Multilayer Perceptron (MLP)’ dahil olmak üzere farklı makine öğrenimi yaklaşımlarının etkinliğini değerlendirmek için ultrason görüntü veri kümesini hazırlandı. Bulgular: RF algoritması, test edilen diğer algoritmalarla karşılaştırıldığında %87,62 ile çok iyi performans göstererek en yüksek doğru görüntü oranını kaydetti. Çalışma genel olarak başarılı kabul edildi ve ortaya çıkan modelin gelişimsel kalça displazisinin erken teşhisinde faydalı olacağına inanılıyor. Sonuç: RF algoritması en yüksek doğru görüntü oranını kaydederek çok iyi bir performans sergilemektedir. Çalışma genel olarak başarılı sayıldı ve elde edilen modelin gelişimsel kalça displazisi’ nin erken teşhisinde yardımcı olacağı düşünülmektedir.

Anahtar Kelimeler

• makine öğrenimi (yapay zeka)
• gelişimsel kalça displazisi
• görüntü sınıflandırma
• lokal ikili model tekniği
• kalça ultrasonografisi

Destekleyen Kurum

yok

Proje Numarası

2017-KAEK-189_2022.02.10_03

Etik Beyan

Çalışma, Yozgat Bozok Üniversitesi Tıp Fakültesi Etik Kurulu tarafından 10.02.2022 tarihinde onaylandı (EK No: 2017-KAEK-189_2022.02.10_03).

Teşekkür

yok

Evaluation of Ultrasound Imaging in Developmental Hip Dysplasia with Artificial Intelligence

Öz

Objective: Developmental hip dysplasia is a common condition that starts in infancy. With the introduction of machine learning (artificial intelligence, AI) into medicine, the early diagnosis of disease and the success of treatment have increased significantly. This study aims to determine the accuracy of ultrasound images from ultrasound videos used in the developmental hip dysplasia screening program using machine learning techniques. Material and Method: The study involved the extraction of ultrasound image features using the Local Binary Pattern (LBP) method. The ultrasound image dataset was then prepared to evaluate the effectiveness of various machine learning approaches, including Decision Tree (DT), Random Forest (RF), K-Nearest Neighbour (KNN), Gradient Boosting (GB), Support Vector Machines (SVM), Naïve Bayes (NB), Logistic Regression (LR), and Multilayer Perceptron (MLP). Results: RF algorithm performed very well, recording the highest correct image rate. The study was generally considered successful and it is believed that the resulting model will be useful in the early diagnosis of developmental hip dysplasia. Conclusion: RF algorithm recorded the highest correct image rate, performing very well at 87.62% compared to other tested algorithms. The study was generally considered successful and the resulting model is believed to be useful in the early diagnosis of developmental hip dysplasia.

Anahtar Kelimeler

• Machine learning (artificial intelligence)
• develeopmental dysplasia of the hip
• image classification
• the local binary pattern technique
• hip ultrasonography

Destekleyen Kurum

none

Proje Numarası

2017-KAEK-189_2022.02.10_03

Etik Beyan

The study was approved by the Yozgat Bozok University Faculty of Medicine Ethics Committee on 10.02.2022 (IRB No. 2017-KAEK-189_2022.02.10_03)

Teşekkür

none

Kaynakça

1. Harsanyi S, Zamborsky R, Krajciova L, Kokavec M, Danisovic L. Developmental Dysplasia of the Hip: A Review of Etiopathogenesis, Risk Factors, and Genetic Aspects. Medicina (Kaunas, Lithuania) 2020; 56.
2. Tao Z, Wang J, Li Y, Zhou Y, et al. Prevalence of developmental dysplasia of the hip (DDH) in infants: a systematic review and meta-analysis. BMJ Paediatr Open 2023;7(1):e002080.
3. He J, Chen T, Lyu X. Analysis of the results of hip ultrasonography in 48 666 infants and efficacy studies of conservative treatment. J Clin Ultrasound 2023;51:656-662.
4. Shipman SA, Helfand M, Moyer VA, Yawn BP. Screening for developmental dysplasia of the hip: a systematic literature review for the US Preventive Services Task Force. Pediatrics 2006;117:e557-576.
5. Omeroğlu H. Use of ultrasonography in developmental dysplasia of the hip. J Child Orthop 2014;8:105-113.
6. Graf R. Classification of hip joint dysplasia by means of sonography. Arch Orthop Trauma Surg (1978) 1984;102:248-255.
7. Jaremko JL, Mabee M, Swami VG, Jamieson L, Chow K, Thompson RB. Potential for change in US diagnosis of hip dysplasia solely caused by changes in probe orientation: patterns of alpha-angle variation revealed by using threedimensional US. Radiology 2014; 273:870-878.
8. Pedrotti L, Crivellari I, Degrate A, De Rosa F, Ruggiero F, Mosconi M. Interpreting neonatal hip sonography: intraobserver and interobserver variability. J Pediatr Orthop B 2020;29:214-218.

9. Arslan RS, Ulutas H, Köksal AS, Bakir M, Çiftçi B. Sensitive deep learning application on sleep stage scoring by using all PSG data. Neural Computing and Applications 2023; 35:7495-7508.
10. Sharma N, Jain V, Mishra A. An analysis of convolutional neural networks for image classification. Procedia computer science 2018;132:377-384.
11. Sezer A, Sezer HB. Deep Convolutional Neural NetworkBased Automatic Classification of Neonatal Hip Ultrasound Images: A Novel Data Augmentation Approach with Speckle Noise Reduction. Ultrasound Med Biol 2020;46:735-749.
12. Pandey M, Fernandez M, Gentile F, et al. The transformational role of GPU computing and deep learning in drug discovery. Nature Machine Intelligence 2022;4:211-221.
13. Ozturk T, Talo M, Yildirim EA, Baloglu UB, Yildirim O, Rajendra Acharya U. Automated detection of COVID-19 cases using deep neural networks with X-ray images. Comput Biol Med 2020;121:103792.
14. Chen T, Zhang Y, Wang B, et al. Development of a Fully Automated Graf Standard Plane and Angle Evaluation Method for Infant Hip Ultrasound Scans. Diagnostics (Basel) 2022; 12.
15. Ladha L, Deepa T. Feature selection methods and algorithms. International journal on Computer Science and Engineering 2011; 3:1787-1797.
16. Ojala T, Pietikäinen M, Harwood D. A comparative study of texture measures with classification based on featured distributions. Pattern Recognition 1996; 29:51-59.
17. Nalepa J, Marcinkiewicz M, Kawulok M. Data Augmentation for Brain-Tumor Segmentation: A Review. Front Comput Neurosci 2019; 13:83.
18. Mucherino, A., Papajorgji, P.J., Pardalos, P.M. (2009). k-Nearest Neighbor Classification. In: Data Mining in Agriculture. Springer Optimization and Its Applications, vol 34. Springer, New York, NY. 2009:83-106.
19. Natekin A, Knoll A. Gradient boosting machines, a tutorial. Frontiers in Neurorobotics 2013;7:21.
20. Breiman L. Random forests. Machine Learning 2001; 45:5-32.
21. Soria D, Garibaldi JM, Ambrogi F, Biganzoli EM, Ellis IO. A ‘non-parametric’version of the naive Bayes classifier. KnowledgeBased Systems 2011; 24:775-784.
22. Mammone A, Turchi M, Cristianini N. Support vector machines. Wiley Interdisciplinary Reviews: Computational Statistics 2009; 1:283-289.
23. Dreiseitl S, Ohno-Machado L. Logistic regression and artificial neural network classification models: a methodology review. Journal of Biomedical Informatics 2002; 35:352-359.
24. Murtagh F. Multilayer perceptrons for classification and regression. Neurocomputing 1991; 2:183-197.
25. Chicco D, Jurman G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics 2020; 21:6.
26. Ruopp MD, Perkins NJ, Whitcomb BW, Schisterman EF. Youden Index and optimal cut-point estimated from observations affected by a lower limit of detection. Biom J 2008; 50:419-430.
27. Lu D, Weng Q. A survey of image classification methods and techniques for improving classification performance. International journal of Remote sensing 2007; 28:823-870.
28. Zhang SC, Sun J, Liu CB, Fang JH, Xie HT, Ning B. Clinical application of artificial intelligence-assisted diagnosis using anteroposterior pelvic radiographs in children with developmental dysplasia of the hip. Bone Joint J 2020; 102-b: 1574-1581.
29. Park HS, Jeon K, Cho YJ, et al. Diagnostic Performance of a New Convolutional Neural Network Algorithm for Detecting Developmental Dysplasia of the Hip on Anteroposterior Radiographs. Korean J Radiol 2021; 22:612-623.
30. Xu W, Shu L, Gong P, et al. A Deep-Learning Aided Diagnostic System in Assessing Developmental Dysplasia of the Hip on Pediatric Pelvic Radiographs. Front Pediatr 2021; 9:785480.
31. Pham TT, Le MB, Le LH, Andersen J, Lou E. Assessment of hip displacement in children with cerebral palsy using machine learning approach. Med Biol Eng Comput 2021; 59:1877-1887.
32. Hu X, Wang L, Yang X, et al. Joint Landmark and Structure Learning for Automatic Evaluation of Developmental Dysplasia of the Hip. IEEE J Biomed Health Inform 2022; 26:345-358.
33. Liu R, Liu M, Sheng B, et al. NHBS-Net: A Feature Fusion Attention Network for Ultrasound Neonatal Hip Bone Segmentation. IEEE Trans Med Imaging 2021; 40:3446-3458.
34. Huang B, Xia B, Qian J, et al. Artificial Intelligence-Assisted Ultrasound Diagnosis on Infant Developmental Dysplasia of the Hip Under Constrained Computational Resources. J Ultrasound Med 2023; 42:1235-1248.