GENERATIVE ADVERSARIAL NETWORKS FOR ANTERIOR CRUCIATE LIGAMENT INJURY DETECTION

Sri Hasta  Mulyani; Mohammad Diqi; Husna Arwa  Salsabil

doi:10.52436/1.jutif.2024.5.1.1150

Sri Hasta Mulyani Dept. of Informatics, Faculty of Science and Technology, Universitas Respati Yogyakarta, Indonesia
Mohammad Diqi Dept. of Informatics, Faculty of Science and Technology, Universitas Respati Yogyakarta, Indonesia
Husna Arwa Salsabil Dept. of Physiotherapy, Faculty of Public Health, Universitas Respati Yogyakarta, Indonesia

DOI: https://doi.org/10.52436/1.jutif.2024.5.1.1150

Keywords: ACL Injury Detection, Anterior Cruciate Ligament, Deep Learning, Generative Adversarial Networks, Medical Image Classification, Unsupervised Learning

Abstract

This research explores the application of Generative Adversarial Networks (GANs) for detecting and classifying Anterior Cruciate Ligament (ACL) injuries using MRI images. The study utilized a dataset of 917 MRI images, each labeled as healthy, partially injured, or completely ruptured, to train the model. The performance of the GAN model was evaluated using a confusion matrix and a classification report, yielding an overall accuracy of 92%. The model demonstrated high proficiency in identifying healthy ACLs and partially injured ACLs but encountered some challenges in accurately identifying completely ruptured ACLs. Despite this, the results suggest that machine learning techniques, particularly GANs, have significant potential for enhancing the accuracy and efficiency of ACL injury detection. The ability of the model to distinguish between different degrees of injury could potentially aid in treatment planning. However, the study also underscores the need for further refinement of the model, particularly in improving its sensitivity in detecting severe ACL injuries. This research highlights the potential of machine learning in medical imaging and provides a solid foundation for future research in ACL injury detection and classification.

Downloads

Download data is not yet available.

References

S. R. Filbay and H. Grindem, “Evidence-based recommendations for the management of anterior cruciate ligament (ACL) rupture,” Best Practice & Research Clinical Rheumatology, vol. 33, no. 1, pp. 33–47, Feb. 2019, doi: 10.1016/j.berh.2019.01.018.

A. M. Montalvo et al., “Anterior Cruciate Ligament Injury Risk in Sport: A Systematic Review and Meta-Analysis of Injury Incidence by Sex and Sport Classification,” Journal of Athletic Training, vol. 54, no. 5, pp. 472–482, Apr. 2019, doi: 10.4085/1062-6050-407-16.

B. Sonnery-Cottet, R. Serra Cruz, T. D. Vieira, R. A. Goes, and A. Saithna, “Ramp Lesions: An Unrecognized Posteromedial Instability?,” Clinics in Sports Medicine, vol. 39, no. 1, pp. 69–81, Jan. 2020, doi: 10.1016/j.csm.2019.08.010.

V. Pedoia, B. Norman, S. N. Mehany, M. D. Bucknor, T. M. Link, and S. Majumdar, “3D convolutional neural networks for detection and severity staging of meniscus and PFJ cartilage morphological degenerative changes in osteoarthritis and anterior cruciate ligament subjects,” Journal of Magnetic Resonance Imaging, vol. 49, no. 2, pp. 400–410, Feb. 2019, doi: 10.1002/jmri.26246.

D. P. Berthold et al., “High Rate of Initially Overlooked Kaplan Fiber Complex Injuries in Patients With Isolated Anterior Cruciate Ligament Injury,” Am J Sports Med, vol. 49, no. 8, pp. 2117–2124, Jul. 2021, doi: 10.1177/03635465211015682.

K.-H. Chen, C. Y. Yang, H.-Y. Wang, H.-L. Ma, and O. K. Lee, “Artificial Intelligence–Assisted Diagnosis of Anterior Cruciate Ligament Tears From Magnetic Resonance Images: Algorithm Development and Validation Study,” Jmir Ai, 2022, doi: 10.2196/37508.

F. R. Espinosa-Leal and K. V. Rodriguez-Alanis, “MR Imaging of Meniscal Tears Associated With Traumatic Anterior Cruciate Ligament Injury,” Journal of the Mexican Federation of Radiology and Imaging, 2023, doi: 10.24875/jmexfri.m23000043.

L. Stijak and P. Schai, “Is There an Influence of the Tibial Slope of the Lateral Condyle on the ACL Lesion?,” Knee Surgery Sports Traumatology Arthroscopy, 2007, doi: 10.1007/s00167-007-0438-1.

M. C. van der Steen, M. Reijman, and R. P. A. Janssen, “Diagnostic Values of History Taking, Physical Examination and KT-1000 Arthrometer for Suspect Anterior Cruciate Ligament Injuries in Children and Adolescents: A Prospective Diagnostic Study,” BMC Musculoskeletal Disorders, 2022, doi: 10.1186/s12891-022-05659-1.

M. H. Hagmeijer et al., “Secondary Meniscal Tears in Patients With Anterior Cruciate Ligament Injury: Relationship Among Operative Management, Osteoarthritis, and Arthroplasty at 18-Year Mean Follow-Up,” The American Journal of Sports Medicine, 2019, doi: 10.1177/0363546519844481.

K. M. Sunbol et al., “Epidemiology of Recurrent Anterior Cruciate Ligament Injuries According to Sport Type,” International Journal of Community Medicine and Public Health, 2022, doi: 10.18203/2394-6040.ijcmph20222087.

S. Jauhiainen, J.-P. Kauppi, T. Krosshaug, R. Bahr, J. Bartsch, and S. " Ayr" am" o, “Predicting ACL Injury Using Machine Learning on Data From an Extensive Screening Test Battery of 880 Female Elite Athletes,” The American Journal of Sports Medicine, vol. 50, no. 11, pp. 2917–2924, Aug. 2022, doi: 10.1177/03635465221112095.

J. Taborri, L. Molinaro, A. Santospagnuolo, M. Vetrano, M. C. Vulpiani, and S. Rossi, “A machine-learning approach to measure the anterior cruciate ligament injury risk in female basketball players,” Sensors, vol. 21, no. 9, 2021, doi: 10.3390/s21093141.

S. S. Mazlan, M. Z. Ayob, and Z. A. Kadir Bakti, “Anterior cruciate ligament (ACL) injury classification system using support vector machine (SVM),” in 2017 International Conference on Engineering Technology and Technopreneurship (ICE2T), IEEE, Sep. 2017. doi: 10.1109/ice2t.2017.8215960.

I. Štajduhar, M. Mamula, D. Mileti’ c, and G. ozde " Unal, “Semi-automated detection of anterior cruciate ligament injury from MRI,” Computer Methods and Programs in Biomedicine, vol. 140, pp. 151–164, Mar. 2017, doi: 10.1016/j.cmpb.2016.12.006.

N. K. Namiri et al., “Deep Learning for Hierarchical Severity Staging of Anterior Cruciate Ligament Injuries from MRI,” Radiology: Artificial Intelligence, vol. 2, no. 4, p. e190207, Jul. 2020, doi: 10.1148/ryai.2020190207.

M. H. Razali, S. M. Sazwan, M. Mahmood, D. Nazri, J. Ali, and M. Z. Ayob, “Anterior cruciate ligament (ACL) coronal view injury diagnosis system using convolutional neural network,” in ACM International Conference Proceeding Series, 2019. doi: 10.1145/3362752.3365196.

H. Koga, T. Muneta, R. Bahr, L. Engebretsen, and T. Krosshaug, “ACL Injury Mechanisms: Lessons Learned from Video Analysis,” in Rotatory Knee Instability, Springer International Publishing, 2016, pp. 27–36. doi: 10.1007/978-3-319-32070-0_3.

V. R. Carlson, F. T. Sheehan, and B. P. Boden, “Video Analysis of Anterior Cruciate Ligament (ACL) Injuries,” JBJS Reviews, vol. 4, no. 11, Nov. 2016, doi: 10.2106/jbjs.rvw.15.00116.

H. Shin, G. S. Choi, and M. C. Chang, “Development of convolutional neural network model for diagnosing tear of anterior cruciate ligament using only one knee magnetic resonance image,” Medicine, vol. 101, no. 44, p. e31510, Nov. 2022, doi: 10.1097/md.0000000000031510.

S. Sridhar et al., “A Torn ACL Mapping in Knee MRI Images Using Deep Convolution Neural Network with Inception-v3,” Journal of Healthcare Engineering, vol. 2022, pp. 1–9, Feb. 2022, doi: 10.1155/2022/7872500.

P. Jaturapisanukul and A. Pangarad, “Reduction of computing resources in convolutional neural network for knee MRI of ACL tears by feature-based method,” in Twelfth International Conference on Digital Image Processing (ICDIP 2020), H. Fujita and X. Jiang, Eds., SPIE, Jun. 2020. doi: 10.1117/12.2573234.

C. Germann et al., “Deep Convolutional Neural Network-Based Diagnosis of Anterior Cruciate Ligament Tears: Performance Comparison of Homogenous Versus Heterogeneous Knee MRI Cohorts with Different Pulse Sequence Protocols and 1.5-T and 3-T Magnetic Field Strengths,” Investigative Radiology, vol. 55, no. 8, 2020, doi: 10.1097/RLI.0000000000000664.

I. Goodfellow et al., “Generative Adversarial Networks,” Communications of the Acm, 2020, doi: 10.1145/3422622.

C. Zheng et al., “Assessment of Generative Adversarial Networks for Synthetic Anterior Segment Optical Coherence Tomography Images in Closed-Angle Detection,” Translational Vision Science & Technology, 2021, doi: 10.1167/tvst.10.4.34.

M. Frid-Adar, I. Diamant, E. Klang, M. Amitai, J. Goldberger, and H. Greenspan, “GAN-based Synthetic Medical Image Augmentation for Increased CNN Performance in Liver Lesion Classification,” Neurocomputing, 2018, doi: 10.1016/j.neucom.2018.09.013.

Z. Ali, S. Naz, H. Zaffar, J. Choi, and Y. Kim, “An IoMT-Based Melanoma Lesion Segmentation Using Conditional Generative Adversarial Networks,” Sensors, 2023, doi: 10.3390/s23073548.

I. R. L. Xu et al., “Generative Adversarial Networks Can Create High Quality Artificial Prostate Cancer Magnetic Resonance Images,” Journal of Personalized Medicine, 2023, doi: 10.3390/jpm13030547.

G. Ahn et al., “High‐resolution Knee Plain Radiography Image Synthesis Using Style Generative Adversarial Network Adaptive Discriminator Augmentation,” Journal of Orthopaedic Research®, 2022, doi: 10.1002/jor.25325.

K. Koshino et al., “Narrative Review of Generative Adversarial Networks in Medical and Molecular Imaging,” Annals of Translational Medicine, 2021, doi: 10.21037/atm-20-6325.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2016, pp. 770–778. doi: 10.1109/CVPR.2016.90.