{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T23:28:03Z","timestamp":1783380483717,"version":"3.54.6"},"reference-count":61,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Diagnosing knee joint osteoarthritis (KOA), a major cause of disability worldwide, is challenging due to subtle radiographic indicators and the varied progression of the disease. Using deep learning for KOA diagnosis requires broad, comprehensive datasets. However, obtaining these datasets poses significant challenges due to patient privacy and data collection restrictions. Additive data augmentation, which enhances data variability, emerges as a promising solution. Yet, it\u2019s unclear which augmentation techniques are most effective for KOA. Our study explored data augmentation methods, including adversarial techniques. We used strategies like horizontal cropping and region of interest (ROI) extraction, alongside adversarial methods such as noise injection and ROI removal. Interestingly, rotations improved performance, while methods like horizontal split were less effective. We discovered potential confounding regions using adversarial augmentation, shown in our models\u2019 accurate classification of extreme KOA grades, even without the knee joint. This indicated a potential model bias towards irrelevant radiographic features. Removing the knee joint paradoxically increased accuracy in classifying early-stage KOA. Grad-CAM visualizations helped elucidate these effects. Our study contributed to the field by pinpointing augmentation techniques that either improve or impede model performance, in addition to recognizing potential confounding regions within radiographic images of knee osteoarthritis.<\/jats:p>","DOI":"10.3390\/a17010008","type":"journal-article","created":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T20:49:27Z","timestamp":1703450967000},"page":"8","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Exploring the Efficacy of Base Data Augmentation Methods in Deep Learning-Based Radiograph Classification of Knee Joint Osteoarthritis"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5295-7192","authenticated-orcid":false,"given":"Fabi","family":"Prezja","sequence":"first","affiliation":[{"name":"Faculty of Information Technology, University of Jyv\u00e4skyl\u00e4, 40014 Jyv\u00e4skyl\u00e4, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8297-8859","authenticated-orcid":false,"given":"Leevi","family":"Annala","sequence":"additional","affiliation":[{"name":"Faculty of Science, Department of Computer Science, University of Helsinki, 00014 Helsinki, Finland"},{"name":"Faculty of Agriculture and Forestry, Department of Food and Nutrition, University of Helsinki, 00014 Helsinki, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sampsa","family":"Kiiskinen","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, University of Jyv\u00e4skyl\u00e4, 40014 Jyv\u00e4skyl\u00e4, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timo","family":"Ojala","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, University of Jyv\u00e4skyl\u00e4, 40014 Jyv\u00e4skyl\u00e4, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,12,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1001\/jamainternmed.2018.7117","article-title":"Deep learning in medicine\u2014promise, progress, and challenges","volume":"179","author":"Wang","year":"2019","journal-title":"JAMA Intern. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1001\/jama.2017.18391","article-title":"Big data and machine learning in health care","volume":"319","author":"Beam","year":"2018","journal-title":"JAMA"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Kather, J.N., Krisam, J., Charoentong, P., Luedde, T., Herpel, E., Weis, C.A., Gaiser, T., Marx, A., Valous, N.A., and Ferber, D. (2019). Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study. PLoS Med., 16.","DOI":"10.1371\/journal.pmed.1002730"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1519","DOI":"10.1038\/s41591-019-0583-3","article-title":"Deep learning-based classification of mesothelioma improves prediction of patient outcome","volume":"25","author":"Courtiol","year":"2019","journal-title":"Nat. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2764","DOI":"10.1038\/s41598-019-39206-1","article-title":"Deep learning in head & neck cancer outcome prediction","volume":"9","author":"Diamant","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"4172","DOI":"10.1038\/s41598-017-04075-z","article-title":"Breast cancer multi-classification from histopathological images with structured deep learning model","volume":"7","author":"Han","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Bakator, M., and Radosav, D. (2018). Deep learning and medical diagnosis: A review of literature. Multimodal Technol. Interact., 2.","DOI":"10.3390\/mti2030047"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"15879","DOI":"10.1038\/s41598-023-42357-x","article-title":"Improved accuracy in colorectal cancer tissue decomposition through refinement of established deep learning solutions","volume":"13","author":"Prezja","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"7511","DOI":"10.3390\/app12157511","article-title":"H&E Multi-Laboratory Staining Variance Exploration with Machine Learning","volume":"12","author":"Prezja","year":"2022","journal-title":"Appl. Sci."},{"key":"ref_12","unstructured":"Prezja, F., Annala, L., Kiiskinen, S., Lahtinen, S., Ojala, T., Ruusuvuori, P., and Kuopio, T. (2023). Improving performance in colorectal cancer histology decomposition using deep and ensemble machine learning. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Liu, X., Song, L., Liu, S., and Zhang, Y. (2021). A review of deep-learning-based medical image segmentation methods. Sustainability, 13.","DOI":"10.3390\/su13031224"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Chuquicusma, M.J.M., Hussein, S., Burt, J., and Bagci, U. (2018, January 4\u20137). How to fool radiologists with generative adversarial networks? A visual turing test for lung cancer diagnosis. Proceedings of the 2018 IEEE 15th International Symposium On Biomedical Imaging (ISBI 2018), Washington, DC, USA.","DOI":"10.1109\/ISBI.2018.8363564"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Calimeri, F., Marzullo, A., Stamile, C., and Terracina, G. (2017, January 11\u201314). Biomedical data augmentation using generative adversarial neural networks. Proceedings of the International Conference on Artificial Neural Networks, Alghero, Italy.","DOI":"10.1007\/978-3-319-68612-7_71"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/j.neucom.2018.09.013","article-title":"GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification","volume":"321","author":"Diamant","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"21896","DOI":"10.1038\/s41598-021-01295-2","article-title":"DeepFake electrocardiograms using generative adversarial networks are the beginning of the end for privacy issues in medicine","volume":"11","author":"Thambawita","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_19","unstructured":"Prezja, F., Annala, L., Kiiskinen, S., Lahtinen, S., and Ojala, T. (2023). Synthesizing Bidirectional Temporal States of Knee Osteoarthritis Radiographs with Cycle-Consistent Generative Adversarial Neural Networks. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Shin, H.C., Tenenholtz, N.A., Rogers, J.K., Schwarz, C.G., Senjem, M.L., Gunter, J.L., Andriole, K.P., and Michalski, M. (2018, January 16). Medical image synthesis for data augmentation and anonymization using generative adversarial networks. Proceedings of the International wOrkshop on Simulation And Synthesis in Medical Imaging, Granada, Spain.","DOI":"10.1007\/978-3-030-00536-8_1"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2378","DOI":"10.1109\/JBHI.2020.2980262","article-title":"Anonymization through data synthesis using generative adversarial networks (ads-gan)","volume":"24","author":"Yoon","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1016\/j.ins.2021.12.018","article-title":"Differentially private synthetic medical data generation using convolutional gans","volume":"586","author":"Torfi","year":"2022","journal-title":"Inf. Sci."},{"key":"ref_23","first-page":"335","article-title":"Generative Adversarial Networks for Creating Synthetic Free-Text Medical Data: A Proposal for Collaborative Research and Re-use of Machine Learning Models","volume":"Volume 2021","author":"Kasthurirathne","year":"2021","journal-title":"Proceedings of the AMIA Annual Symposium Proceedings"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"18573","DOI":"10.1038\/s41598-022-23081-4","article-title":"DeepFake knee osteoarthritis X-rays from generative adversarial neural networks deceive medical experts and offer augmentation potential to automatic classification","volume":"12","author":"Prezja","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4931437","DOI":"10.1155\/2021\/4931437","article-title":"Emergence of deep learning in knee osteoarthritis diagnosis","volume":"2021","author":"Yeoh","year":"2021","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.joca.2009.08.003","article-title":"Depth-wise progression of osteoarthritis in human articular cartilage: Investigation of composition, structure and biomechanics","volume":"18","author":"Saarakkala","year":"2010","journal-title":"Osteoarthr. Cartil."},{"key":"ref_27","first-page":"133","article-title":"Biomechanical properties of knee articular cartilage","volume":"40","author":"Laasanen","year":"2003","journal-title":"Biorheology"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1745","DOI":"10.1016\/S0140-6736(19)30417-9","article-title":"Osteoarthritis","volume":"393","author":"Hunter","year":"2019","journal-title":"Lancet"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1002\/acr.21617","article-title":"Productivity costs and medical costs among working patients with knee osteoarthritis","volume":"64","author":"Hermans","year":"2012","journal-title":"Arthritis Care Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"20038","DOI":"10.1038\/s41598-019-56527-3","article-title":"Multimodal machine learning-based knee osteoarthritis progression prediction from plain radiographs and clinical data","volume":"9","author":"Tiulpin","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1727","DOI":"10.1038\/s41598-018-20132-7","article-title":"Automatic knee osteoarthritis diagnosis from plain radiographs: A deep learning-based approach","volume":"8","author":"Tiulpin","year":"2018","journal-title":"Sci. Rep."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Tiulpin, A., and Saarakkala, S. (2020). Automatic grading of individual knee osteoarthritis features in plain radiographs using deep convolutional neural networks. Diagnostics, 10.","DOI":"10.3390\/diagnostics10110932"},{"key":"ref_33","unstructured":"Prezja, F., Annala, L., Kiiskinen, S., Lahtinen, S., and Ojala, T. (2023). Adaptive Variance Thresholding: A Novel Approach to Improve Existing Deep Transfer Vision Models and Advance Automatic Knee-Joint Osteoarthritis Classification. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1195923","DOI":"10.3389\/fneur.2023.1195923","article-title":"Detection of brain regions responsible for chronic pain in osteoarthritis: An fMRI-based neuroimaging study using deep learning","volume":"14","author":"Chatterjee","year":"2023","journal-title":"Front. Neurol."},{"key":"ref_35","unstructured":"Centers for Disease Control and Prevention (2003). HIPAA privacy rule and public health. Guidance from CDC and the US Department of Health and Human Services. MMWR Morb. Mortal. Wkly. Rep., 52, 1\u201317."},{"key":"ref_36","first-page":"10","article-title":"The EU general data protection regulation (GDPR)","volume":"Volume 10","author":"Voigt","year":"2017","journal-title":"A Practical Guide"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"12561","DOI":"10.1007\/s10462-023-10453-z","article-title":"Medical image data augmentation: Techniques, comparisons and interpretations","volume":"56","author":"Goceri","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"ref_38","first-page":"979","article-title":"Differential data augmentation techniques for medical imaging classification tasks","volume":"Volume 2017","author":"Hussain","year":"2017","journal-title":"Proceedings of the AMIA Annual Symposium Proceedings"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Wahyuningrum, R.T., Anifah, L., Purnama, I.K.E., and Purnomo, M.H. (2019, January 23\u201325). A new approach to classify knee osteoarthritis severity from radiographic images based on CNN-LSTM method. Proceedings of the 2019 IEEE 10th International Conference on Awareness Science and Technology (iCAST), Morioka, Japan.","DOI":"10.1109\/ICAwST.2019.8923284"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chetouani, A., and Jennane, R. (2023). Transformer with Selective Shuffled Position Embedding using ROI-Exchange Strategy for Early Detection of Knee Osteoarthritis. arXiv.","DOI":"10.1109\/ISBI52829.2022.9761626"},{"key":"ref_41","unstructured":"Finlayson, S.G., Chung, H.W., Kohane, I.S., and Beam, A.L. (2018). Adversarial attacks against medical deep learning systems. arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Hirano, H., Minagi, A., and Takemoto, K. (2021). Universal adversarial attacks on deep neural networks for medical image classification. BMC Med. Imaging, 21.","DOI":"10.1186\/s12880-020-00530-y"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Paschali, M., Conjeti, S., Navarro, F., and Navab, N. (2018, January 16\u201320). Generalizability vs. robustness: Investigating medical imaging networks using adversarial examples. Proceedings of the Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2018: 21st International Conference, Granada, Spain. Proceedings, Part I.","DOI":"10.1007\/978-3-030-00928-1_56"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1287","DOI":"10.1126\/science.aaw4399","article-title":"Adversarial attacks on medical machine learning","volume":"363","author":"Finlayson","year":"2019","journal-title":"Science"},{"key":"ref_45","unstructured":"Nevitt, M., Felson, D., and Lester, G. (2023, April 29). The Osteoarthritis Initiative, Available online: https:\/\/nda.nih.gov\/static\/docs\/StudyDesignProtocolAndAppendices.pdf."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1136\/ard.16.4.494","article-title":"Radiological assessment of osteo-arthrosis","volume":"16","author":"Kellgren","year":"1957","journal-title":"Ann. Rheum. Dis."},{"key":"ref_47","unstructured":"Tan, M., and Le, Q. (2021, January 18\u201324). Efficientnetv2: Smaller models and faster training. Proceedings of the International Conference on Machine Learning (PMLR 2021), Online."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.compmedimag.2019.06.002","article-title":"Fully automatic knee osteoarthritis severity grading using deep neural networks with a novel ordinal loss","volume":"75","author":"Chen","year":"2019","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_50","first-page":"1995","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"LeCun","year":"1995","journal-title":"Handb. Brain Theory Neural Netw."},{"key":"ref_51","unstructured":"Goodfellow, I.J., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_52","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning (PMLR 2019), Long Beach, CA, USA."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018, January 18\u201322). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_54","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_55","unstructured":"Prezja, F. (2023, April 29). Deep Fast Vision: Accelerated Deep Transfer Learning Vision Prototyping and Beyond. Available online: https:\/\/github.com\/fabprezja\/deep-fast-vision."},{"key":"ref_56","unstructured":"Chollet, F. (2023, April 26). Keras. Available online: https:\/\/keras.io."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision And Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Oquab, M., Bottou, L., Laptev, I., and Sivic, J. (2015, January 7\u201312). Is Object Localization for Free?\u2014Weakly-Supervised Learning With Convolutional Neural Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298668"},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Zech, J.R., Badgeley, M.A., Liu, M., Costa, A.B., Titano, J.J., and Oermann, E.K. (2018). Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study. PLoS Med., 15.","DOI":"10.1371\/journal.pmed.1002683"},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Chattopadhay, A., Sarkar, A., Howlader, P., and Balasubramanian, V.N. (2018, January 12\u201315). Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks. Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA.","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"867","DOI":"10.1038\/s42256-022-00536-x","article-title":"Benchmarking saliency methods for chest X-ray interpretation","volume":"4","author":"Saporta","year":"2022","journal-title":"Nat. Mach. Intell."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/1\/8\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:41:16Z","timestamp":1760132476000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/1\/8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,24]]},"references-count":61,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,1]]}},"alternative-id":["a17010008"],"URL":"https:\/\/doi.org\/10.3390\/a17010008","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,24]]}}}