Classifying the Severity of Knee Osteoarthritis on X-ray Images Using NASNet Mobile
DOI:
https://doi.org/10.30871/jaic.v10i2.12246Keywords:
CNN, K-fold Cross Validation, Knee Osteoarthritis, NASNet MobileAbstract
Knee osteoarthritis is a joint condition characterized by cartilage breakdown in the knee, most frequently affecting older adults. Early diagnosis of knee osteoarthritis is critical because it can delay disease progression and improve patient quality of life. This study aims to classify the severity of knee osteoarthritis using X-ray images by employing a Convolutional Neural Network (CNN) with the NASNet Mobile model. The dataset consists of 1500 knee X-ray images, divided into three classes: normal, moderate, and severe. The model was trained with various batch sizes and learning rates. The highest accuracy of 92.53% was achieved on the k-fold cross-validation dataset using a batch size of 32 and a learning rate of 0.001, yielding a sensitivity of 92.72% and a specificity of 96.32%.
Downloads
References
[1] A. Tiwari, M. Poduval, and V. Bagaria, “Evaluation of Artificial Intelligence Models for Osteoarthritis of The Knee Using Deep Learning Algorithms for Orthopedic Radiographs,” World J. Orthop., vol. 13, no. 6, pp. 603–614, 2022, doi: 10.5312/WJO.V13.I6.603.
[2] S. M. Ahmed and R. J. Mstafa, “A Comprehensive Survey on Bone Segmentation Techniques in Knee Osteoarthritis Research: From Conventional Methods to Deep Learning,” Diagnostics, vol. 12, no. 3, 2022, doi: 10.3390/diagnostics12030611.
[3] I. N. Ackerman, J. L. Kemp, K. A. Y. M. Crossley, A. G. Culvenor, and R. S. Hinman, “Hip and Knee Osteoarthritis Affects Younger People, Too,” vol. 47, no. 2, pp. 67–79, 2017, doi: 10.2519/jospt.2017.7286.
[4] T. N. Cao, K. N. Huynh, H. T. Tran, and M. D. Nguyen, “Association Between Asymptomatic Hyperuricemia and Knee Osteoarthritis in Older Outpatients,” Eur. Rev. Med. Pharmacol. Sci., vol. 26, no. 18, pp. 6600–6607, 2022, doi: 10.26355/eurrev_202209_29760.
[5] M. Ganesh Kumar and A. Das Goswami, “Automatic Classification of the Severity of Knee Osteoarthritis Using Enhanced Image Sharpening and CNN,” Appl. Sci., vol. 13, no. 3, 2023, doi: 10.3390/app13031658.
[6] V. K. V, V. Kalpana, and G. H. Kumar, “Evaluating the Efficacy of Deep Learning Models for Knee Osteoarthritis Prediction Based on Kellgren-Lawrence Grading System,” e-Prime - Adv. Electr. Eng. Electron. Energy, vol. 5, no. July, p. 100266, 2023, doi: 10.1016/j.prime.2023.100266.
[7] H. Zhao, L. Ou, Z. Zhang, L. Zhang, K. Liu, and J. Kuang, “The value of deep learning-based X-ray techniques in detecting and classifying K-L grades of knee osteoarthritis: a systematic review and meta-analysis,” Eur. Radiol., vol. 35, no. 1, pp. 327–340, 2025, doi: 10.1007/s00330-024-10928-9.
[8] B. H. Do, C. Langlotz, and C. F. Beaulieu, “Bone Tumor Diagnosis Using a Naïve Bayesian Model of Demographic and Radiographic Features,” J. Digit. Imaging, vol. 30, no. 5, pp. 640–647, 2017, doi: 10.1007/s10278-017-0001-7.
[9] J. Langhorn, A. Borjali, E. Hippensteel, W. Nelson, and B. Raeymaekers, “Microtextured CoCrMo Alloy for Use in Metal-on-Polyethylene Prosthetic Joint Bearings: Multi-Directional Wear and Corrosion Measurements,” Tribol Int., vol. 124, pp. 178–183, 2018, doi: 10.1016/j.triboint.2018.04.007.Microtextured.
[10] Y. Xue, R. Zhang, Y. Deng, K. Chen, and T. Jiang, “A Preliminary Examination of The Diagnostic Value of Deep Learning in Hip Osteoarthritis,” PLoS One, vol. 12, no. 6, pp. 1–9, 2017, doi: 10.1371/journal.pone.0178992.
[11] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT press., 2016. [Online]. Available: https://scholar.google.com/scholar_lookup?title=Deep+Learning&author=Goodfellow,+I.&author=Bengio,+Y.&author=Courville,+A.&publication_year=2016
[12] D. Saha, M. P. Mangukia, and A. Manickavasagan, “Real-Time Deployment of MobileNetV3 Model in Edge Computing Devices Using RGB Color Images for Varietal Classification of Chickpea,” Appl. Sci., vol. 13, no. 13, pp. 1–16, 2023, doi: 10.3390/app13137804.
[13] K. Radhika, K. Devika, T. Aswathi, P. Sreevidya, V. Sowmya, and K. P. Soman, Performance Analysis of NASNet on Unconstrained Ear Recognition, vol. 871. Springer International Publishing, 2020. doi: 10.1007/978-3-030-33820-6_3.
[14] A. O. Adedoja, P. A. Owolawi, T. Mapayi, and C. Tu, “Intelligent Mobile Plant Disease Diagnostic System Using NASNet-Mobile Deep Learning,” IAENG Int. J. Comput. Sci., vol. 49, no. 1, pp. 216–231, 2022.
[15] S. Dümen, E. K. Yilmaz, K. Adem, and E. Avaroglu, “Achieving High Accuracy in Lemon Quality Classification : A Comparative Study of Deep Learning and Transformer Models,” Res. Sq., pp. 1–20, 2023.
[16] M. M. Ahsan, K. D. Gupta, M. M. Islam, S. Sen, M. L. Rahman, and M. Shakhawat Hossain, “COVID-19 Symptoms Detection Based on NasNetMobile with Explainable AI Using Various Imaging Modalities,” Mach. Learn. Knowl. Extr., vol. 2, no. 4, pp. 490–504, 2020, doi: 10.3390/make2040027.
[17] S. Bharati, P. Podder, M. R. Mondal, and H. N. Gandhi, “Optimized NASNet for Diagnosis of COVID-19 from Lung CT Images,” in Advances in Intelligent Systems and Computing, 2021. doi: 10.1007/978-3-030-71187-0_9.
[18] A. Yilmaz, M. Kalebasi, Y. Samoylenko, M. E. Guvenilir, and H. Uvet, “Benchmarking of Lightweight Deep Learning Architectures for Skin Cancer Classification using ISIC 2017 Dataset,” arXiv, 2021, [Online]. Available: http://arxiv.org/abs/2110.12270
[19] P. Anantha Prabha, G. Suchitra, and R. Saravanan, “Cephalopods Classification Using Fine Tuned Lightweight Transfer Learning Models,” Intell. Autom. Soft Comput., vol. 35, no. 3, pp. 3065–3079, 2023, doi: 10.32604/iasc.2023.030017.
[20] S. Kumar, “Knee Osteoarthritis Dataset (Preprocessed-128x128).” [Online]. Available: https://www.kaggle.com/datasets/sachinkumar413/knee-osteoarthritis-dataset-preprocessed128x128?resource=download
[21] P. Chen, “Knee Osteoarthritis Severity Grading Dataset,” Mendeley Data.
[22] J. Yoonsuh, “Multiple Predicting K-fold Cross-Validation for Model Selection,” J. Nonparametr. Stat., vol. 30, no. 1, pp. 197–215, 2017, [Online]. Available: https://www.tandfonline.com/doi/full/10.1080/10485252.2017.1404598
[23] S. Mohapatra, G. Kumar Pati, M. Mishra, and T. Swarnkar, “Gastrointestinal Abnormality Detection and Classification Using Empirical Wavelet Transform and Deep Convolutional Neural Network from Endoscopic Images,” Ain Shams Eng. J., vol. 14, no. 4, p. 101942, 2023, doi: 10.1016/j.asej.2022.101942.
[24] D. C. R. Novitasari et al., “Image Fundus Classification System for Diabetic Retinopathy Stage Detection Using Hybrid CNN-DELM,” Big Data Cogn. Comput., vol. 6, no. 4, 2022, doi: 10.3390/bdcc6040146.
[25] D. Singh and B. Singh, “Investigating the impact of data normalization on classification performance,” Appl. Soft Comput., vol. 97, 2020, doi: 10.1016/j.asoc.2019.105524.
[26] S. N. Fadilah, D. C. R. Novitasari, and L. Hakim, “Pengaruh Reduksi Fitur Pada Klasifikasi Kanker Paru Menggunakan CNN Dengan Arsitektur GoogLeNet,” J. Fourier, vol. 12, no. 1, pp. 20–32, 2023, doi: 10.14421/fourier.2023.121.20-32.
[27] D. Z. Haq, “Klasifikasi Citra Kanker Kulit Menggunakan Convolutional Neural Network Model Googlenet,” UIN Sunan Ampel Surabaya, 2021.
[28] X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, A review of convolutional neural networks in computer vision, vol. 57, no. 4. Springer Netherlands, 2024. doi: 10.1007/s10462-024-10721-6.
[29] Q. Gao, S. Lim, and X. Jia, “Hyperspectral Image Classification Using Convolutional Neural Networks and Multiple Feature Learning,” Remote Sens., vol. 10, no. 2, 2018, doi: 10.3390/rs10020299.
[30] S. Albawi, T. A. Mohammed, and S. Al-Zawi, “Understanding of A Convolutional Neural Network,” Proc. 2017 Int. Conf. Eng. Technol. ICET 2017, pp. 1–6, 2018, doi: 10.1109/ICEngTechnol.2017.8308186.
[31] Q. Sellat, S. K. Bisoy, and R. Priyadarshini, “Semantic Segmentation for Self-Driving Cars using Deep Learning: A Survey,” in Cognitive Big Data Intelligence with a Metaheuristic Approach, 2021. doi: 10.1016/B978-0-323-85117-6.00002-9.
[32] M. M. Taye, “Theoretical Understanding of Convolutional Neural Network: Concepts, Architectures, Applications, Future Directions,” Computation, vol. 11, no. 3, 2023, doi: 10.3390/computation11030052.
[33] F. Sultana, A. Sufian, and P. Dutta, “Advancements in Image Classification Using Convolutional Neural Network,” in Proceedings - 2018 4th IEEE International Conference on Research in Computational Intelligence and Communication Networks, ICRCICN 2018, IEEE, 2018, pp. 122–129. doi: 10.1109/ICRCICN.2018.8718718.
[34] B. Zoph, V. Vasudevan, J. Shlens, and Q. V Le, “Learning Transferable Architectures for Scalable Image Recognition,” Proc. IEEE Conf. Comput. Vis. pattern Recognit., pp. 8697–8710, 2018.
[35] Y. T. Chen et al., “Deep Learning–based Brain Computed Tomography Image Classification with Hyperparameter Optimization through Transfer Learning for Stroke,” Diagnostics, vol. 12, no. 4, 2022, doi: 10.3390/diagnostics12040807.
[36] V. Anand, S. Gupta, A. Altameem, S. R. Nayak, R. C. Poonia, and A. K. J. Saudagar, “An Enhanced Transfer Learning based Classification for Diagnosis of Skin Cancer,” Diagnostics, vol. 12, no. 7, 2022, doi: 10.3390/diagnostics12071628.
[37] T. Putra, Suprapto, and A. Bukhori, “Model Klasifikasi Berbasis Multiclass Classification dengan Kombinasi Indobert Embedding dan Long Short-Term Memory untuk Tweet Berbahasa Indonesia,” J. Ilmu Siber dan Teknol. Digit., vol. 1, no. 1, pp. 1–28, 2022, [Online]. Available: https://penerbitgoodwood.com/index.php/jisted/article/view/1509/369
[38] N. Iyer, V. Thejas, N. Kwatra, R. Ramjee, and M. Sivathanu, “Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule,” J. Mach. Learn. Res., vol. 24, pp. 1–37, 2023, [Online]. Available: http://arxiv.org/abs/2003.03977
[39] Y. Wu et al., “Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks,” Proc. - 2019 IEEE Int. Conf. Big Data, Big Data 2019, pp. 1971–1980, 2019, doi: 10.1109/BigData47090.2019.9006104.
[40] Karsito and Susanti Santi, “Klasifikasi Kelayakan Peserta Pengajuan Kredit Rumah Dengan Algoritma Naive Bayes Di Perumahan Azzura Residence,” J. Teknol. Pelita Bangsa, vol. 9, pp. 43–48, 2019.
[41] Styawati, N. Hendrastuty, A. Rahman Isnain, and A. Yanti Rahmadhani, “Analisis Sentimen Masyarakat Terhadap Program Kartu Prakerja Pada Twitter Dengan Metode Support Vector Machine,” J. Inform. J. Pengemb. IT, vol. 6, no. 3, pp. 150–155, 2021, [Online]. Available: http://situs.com
[42] K. R. Mahmudah, B. Purnama, F. Indriani, and K. Satou, “Machine Learning Algorithms for Predicting Chronic Obstructive Pulmonary Disease from Gene Expression Data with Class Imbalance,” in 12th International Conference on Bioinformatics Models, Methods and Algorithms; Part of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2021, 2021, pp. 148–153. doi: 10.5220/0010316501480153.
[43] O. Sule and S. Viriri, “Enhanced Convolutional Neural Networks for Segmentation of Retinal Blood Vessel Image,” 2020 Conf. Inf. Commun. Technol. Soc. ICTAS 2020 - Proc., pp. 0–5, 2020, doi: 10.1109/ICTAS47918.2020.233996.
[44] S. Qummar et al., “A Deep Learning Ensemble Approach for Diabetic Retinopathy Detection,” IEEE Access, vol. 7, pp. 150530–150539, 2019, doi: 10.1109/ACCESS.2019.2947484.
[45] N. Sakinah, T. Badriyah, and I. Syarif, “Analisis Kinerja Algoritma Mesin Pembelajaran untuk Klarifikasi Penyakit Stroke Menggunakan Citra CT Scan,” J. Teknol. Inf. dan Ilmu Komput., vol. 7, no. 4, p. 833, 2020, doi: 10.25126/jtiik.2020743482.
[46] Y. Xiao et al., “A New Color Augmentation Method For Deep Learning Segmentation Of Histological Images,” in IEEE 16th International Symposium on Biomedical Imaging, 2019, pp. 886–890.
[47] H. A. Morsy, “Comparison of Commonly Used Non-Adaptive Image Scaling Techniques,” CiiT Int. J. Digit. Image Process., vol. 10, no. 9, pp. 177–180, 2018, [Online]. Available: https://www.researchgate.net/publication/344324331_Comparison_of_commonly_used_non-adaptive_image_scaling_techniques
[48] D. Umamaheswari and D. S. Geetha, “Segmentation and Classification of Acute Lymphoblastic Leukemia Cells Tooled with Digital Image Processing and ML Techniques,” Proc. Second Int. Conf. Intell. Comput. Control Syst. (ICICCS 2018), 2018, doi: 10.1201/9781439802069-1.
[49] A. Haseeb et al., “Knee Osteoarthritis Classification Using X-Ray Images Based on Optimal Deep Neural Network,” Comput. Syst. Sci. Eng., vol. 47, no. 2, pp. 2397–2415, 2023, doi: 10.32604/csse.2023.040529.
[50] S. W. Pi, B. D. Lee, M. S. Lee, and H. J. Lee, “Ensemble deep-learning networks for automated osteoarthritis grading in knee X-ray images,” Sci. Rep., vol. 13, no. 1, pp. 1–17, 2023, doi: 10.1038/s41598-023-50210-4.
[51] S. Kinger, “Deep Learning for Automatic Knee Osteoarthritis Severity Grading and Classification,” Indian J. Orthop., vol. 58, no. 10, pp. 1458–1473, 2024, doi: 10.1007/s43465-024-01259-4.
[52] S. M. Ahmed and R. J. Mstafa, “Identifying Severity Grading of Knee Osteoarthritis from X-ray Images Using an Efficient Mixture of Deep Learning and Machine Learning Models,” Diagnostics, vol. 12, no. 12, 2022, doi: 10.3390/diagnostics12122939.
[53] S. Rani et al., “Deep learning to combat knee osteoarthritis and severity assessment by using CNN-based classification,” BMC Musculoskelet. Disord., vol. 25, no. 1, 2024, doi: 10.1186/s12891-024-07942-9.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Adelia Damayanti, Dian Candra Rini Novitasari, Lutfi Hakim, Musfiroh Musfiroh
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
