Localization and classification of epiphyses in carpal radiographs using YOLO models
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1336Keywords:
bone age, epiphysis, Object detectionAbstract
Objective: This study proposes the development of a model for detecting epiphyses in X-ray images using machine learning models. Methods: We describe the process of dataset acquisition and conduct tests with models such as YOLOv5, YOLOv8, and Faster R-CNN. Results: The YOLOv8 model achieved a 1% error rate on the DHA dataset, while the YOLOv5 model achieved around 5%. Conclusion: After a comparative analysis, YOLOv8 was selected as the ideal model for final epiphyses detection.
References
Hossain A, Islam MT, Almutairi AF. A deep learning model to classify and detect brain abnormalities in portable microwave based imaging system. 2022. Scientific Reports.
Jones J, Greulich and Pyle method. 2020.
Koitka S, Kim MS. Qu M. Fischer A, Friedrich CM, Nensa F. Mimicking the radiologists’ workflow: Estimating pediatric hand bone age with stacked deep neural networks. 2020. Medical Image Analysis 64.
Pinto, Vanessa C. Relação da idade óssea e marcadores hormonais com a capacidade física de adolescentes. 2017. J Hum Growth Dev.
Redmon J, Divvala S, Girshick R, Farhadi A. You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. (CVPR).
Schneider, R, Irigaray, T. Envelhecimento na atualidade: aspectos cronológicos, biológicos, psicológicos e sociais. Estudos de psicologia. 2008.
Chollet, F. Deep Learning with Python. 2017.
Trombetta GBW, Fröhlich W da R, Rigo SJ, Rodrigues CA. Aplicação de Deep Learning para Diagnóstico de Pneumonia Causada por COVID -19 a partir de Imagens de Raio X. J Health Inform [Internet]. 15º de março de 2021 [citado 21º de maio de 2024];12. Disponível em: https://jhi.sbis.org.br/index.php/jhi-sbis/article/view/828
https://www.rsna.org/rsnai/ai-image-challenge/rsna-pediatric-bone-age-challenge-2017.
Koitka S, Demircioglu A, Kim MS, Friedrich CM, Nensa F.Ossification area localization in pediatric hand radiographs using deep neural networks for object detection. 2018.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
