{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T13:11:40Z","timestamp":1779282700963,"version":"3.51.4"},"reference-count":30,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:00:00Z","timestamp":1779235200000},"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>Osteoarthritis (OA) severity grading from hand distal interphalangeal (DIP) joint radiographs using the Kellgren\u2013Lawrence (KL) scale is challenged by severe class imbalance, with higher grades (KL3 and KL4) markedly underrepresented in clinical datasets. To address this limitation, we propose a VGG19-based classification framework that systematically evaluates six training strategies targeting imbalance at the data level, algorithmic level, or in combination. Synthetic images for minority classes were generated using CycleGAN and subsequently filtered through rheumatologist validation. The evaluated strategies include baseline training, rheumatologist-validated synthetic augmentation (SD), oversampling (OS), focal loss (FL) optimization, and multiple combinations of these approaches. The results show that strategies incorporating oversampling demonstrated the most consistent and statistically robust improvements in minority-class performance. Specifically, the combination of synthetic data and oversampling (SD + OS) achieved the highest binary OA sensitivity (96.12%) and significantly improved OA F1 score compared to baseline (0.613 vs. 0.416, p = 0.029). The full combined strategy (SD + OS + FL) yielded the highest KL3 F1 score (0.527 vs. 0.280 baseline, p = 0.048) and significantly improved KL4 F1 score (0.730 vs. 0.570 baseline, p = 0.150). Importantly, all strategies maintained higher or similar overall performance with no significant change in majority-class performance (p &gt; 0.10), indicating that improvements in minority classes were not achieved at the expense of sacrificing majority classes or overall model reliability. These findings suggest that the proposed imbalance-mitigation strategies may improve minority class OA detection, particularly when oversampling and validated synthetic augmentation are combined. It is worth noting that the above results are derived from a held-out test set comprising 1626 samples, among which only 43 are OA-positive due to data imbalance. The results should be treated as preliminary findings subject to change upon validation in larger cohorts of OA patients.<\/jats:p>","DOI":"10.3390\/a19050414","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T12:30:51Z","timestamp":1779280251000},"page":"414","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Classification of Hand Osteoarthritis Using Deep Learning with Synthesized Data and Focal Loss Optimization"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0187-8110","authenticated-orcid":false,"given":"Hetali","family":"Tank","sequence":"first","affiliation":[{"name":"Department of Computer Science, Seidenberg School of CSIS, Pace University, New York, NY 10038, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Boston University, Boston, MA 02215, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2718-3164","authenticated-orcid":false,"given":"Juan","family":"Shan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Seidenberg School of CSIS, Pace University, New York, NY 10038, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Boston University, Boston, MA 02215, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1002\/art.41142","article-title":"2019 American College of Rheumatology\/Arthritis Foundation Guideline for the management of osteoarthritis of the hand, hip, and knee","volume":"72","author":"Kolasinski","year":"2020","journal-title":"Arthritis Rheumatol."},{"key":"ref_2","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_3","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.1136\/ard.2011.150078","article-title":"Prevalence, incidence and progression of hand osteoarthritis in the general population: The Framingham Osteoarthritis Study","volume":"70","author":"Haugen","year":"2011","journal-title":"Ann. Rheum. Dis."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1886","DOI":"10.1007\/s11999-016-4732-4","article-title":"Classifications in brief: Kellgren\u2013Lawrence classification of osteoarthritis","volume":"474","author":"Kohn","year":"2016","journal-title":"Clin. Orthop. Relat. Res."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1007\/s11547-022-01476-7","article-title":"Automatic detection and classification of knee osteoarthritis using deep learning approach","volume":"127","author":"Abdullah","year":"2022","journal-title":"Radiol. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Guida, C., Zhang, M., Blackadar, J., Yang, Z., Driban, J.B., Duryea, J., and Shan, J. (2021, January 13\u201316). Automated hand osteoarthritis classification using convolutional neural networks. Proceedings of the 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA), Pasadena, CA, USA.","DOI":"10.1109\/ICMLA52953.2021.00240"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/s10462-024-10884-2","article-title":"Handling imbalanced medical datasets: Review of a decade of research","volume":"57","author":"Salmi","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s40537-019-0192-5","article-title":"Survey on deep learning with class imbalance","volume":"6","author":"Johnson","year":"2019","journal-title":"J. Big Data"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22\u201329). Unpaired image-to-image translation using Cycle-consistent adversarial networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ma, Y., Liu, Y., Cheng, J., Zheng, Y., Ghahremani, M., Chen, H., Liu, J., and Zhao, Y. (2020). Cycle structure and illumination constrained GAN for medical image enhancement. Proceedings of the Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2020, Lima, Peru, 4\u20138 October 2020, Springer. Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-030-59713-9_64"},{"key":"ref_12","unstructured":"Galdran, A., Carneiro, G., and Ballester, M.A.G. (October, January 27). Balanced-MixUp for highly imbalanced medical image classification. Proceedings of the Medical Image Computing and Computer Assisted Intervention\u2014MICCAI, Strasbourg, France."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chartsias, A., Joyce, T., Dharmakumar, R., and Tsaftaris, S.A. (2017, January 10). Adversarial image synthesis for unpaired multi-modal cardiac data. Proceedings of the Simulation and Synthesis in Medical Imaging, Qu\u00e9bec City, QC, Canada.","DOI":"10.1007\/978-3-319-68127-6_1"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Hu, J., Xiao, F., Jin, Q., Zhao, G., and Lou, P. (2023). Synthetic data generation based on RDB-CycleGAN for industrial object detection. Mathematics, 11.","DOI":"10.3390\/math11224588"},{"key":"ref_15","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_16","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_17","first-page":"103820","article-title":"Development and validation of a deep learning system to screen multi-class retinal diseases using optical coherence tomography macular images","volume":"119","author":"Zhou","year":"2021","journal-title":"J. Biomed. Inform."},{"key":"ref_18","first-page":"2045","article-title":"Focal loss analysis of nerve fiber layer reflectance for glaucoma diagnosis","volume":"12","author":"Tan","year":"2021","journal-title":"Biomed. Opt. Express"},{"key":"ref_19","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Mateen, M., Wen, J., Nasrullah, N., Song, S., and Huang, Z. (2019). Fundus image classification using VGG-19 architecture with PCA and SVD. Symmetry, 11.","DOI":"10.3390\/sym11010001"},{"key":"ref_21","first-page":"96","article-title":"Evolving medical image classification: A three-tiered framework combining MSPLnet and IRNet-VGG19","volume":"48","author":"Annapoorani","year":"2024","journal-title":"J. Med. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chandrasekaran, S., Aarathi, S., Alqhatani, A., Khan, S.B., Quasim, M.T., and Basheer, S. (2025). Improving healthcare sustainability using advanced brain simulations with VGG19 and bidirectional LSTM. Front. Med., 12.","DOI":"10.3389\/fmed.2025.1574428"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kim, H.E., Cosa-Linan, A., Santhanam, N., Jannesari, M., Maros, M.E., and Ganslandt, T. (2022). Transfer learning for medical image classification: A literature review. BMC Med. Imaging, 22.","DOI":"10.1186\/s12880-022-00793-7"},{"key":"ref_24","unstructured":"Cao, Z., Shan, J., Jiang, X., Wang, Q., McAlindon, T., Driban, J., and Zhang, M. (2025). Enhancing Hand Osteoarthritis Classification with Generative AI: A CycleGAN and EfficientNetB7 Approach [abstract]. Arthritis Rheumatol., 77."},{"key":"ref_25","unstructured":"(2026, May 15). OAI\u2014The Osteoarthritis Initiative. National Institute of Mental Health Data Archive (NDA), Available online: https:\/\/nda.nih.gov\/oai\/."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"422","DOI":"10.3899\/jrheum.180240","article-title":"Characteristics of accelerated hand osteoarthritis: Data from the osteoarthritis initiative","volume":"46","author":"Davis","year":"2019","journal-title":"J. Rheumatol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"104713","DOI":"10.1016\/j.bspc.2023.104713","article-title":"Automatic measuring of finger joint space width on hand radiograph using deep learning and conventional computer vision methods","volume":"84","author":"Ponnusamy","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"He, W., Zhou, T., Xiang, Y., Lin, Y., Hu, J., and Bao, R. (2024). Deep learning in image classification: Evaluating VGG19\u2032s performance on complex visual data. arXiv.","DOI":"10.1109\/NNICE64954.2025.11064681"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Khan, M.A., Rajinikanth, V., Satapathy, S.C., Taniar, D., Mohanty, J.R., Tariq, U., and Dama\u0161evi\u010dius, R. (2021). VGG19 network assisted joint segmentation and classification of lung nodules in CT images. Diagnostics, 11.","DOI":"10.3390\/diagnostics11122208"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3609","DOI":"10.1007\/s12652-021-03488-z","article-title":"Transfer learning for image classification using VGG19: Caltech-101 image dataset","volume":"14","author":"Bansal","year":"2023","journal-title":"J. Ambient. Intell. Humaniz. Comput."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/5\/414\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T12:40:57Z","timestamp":1779280857000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/5\/414"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,20]]},"references-count":30,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["a19050414"],"URL":"https:\/\/doi.org\/10.3390\/a19050414","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,20]]}}}