Ensuring Accuracy in AI-Based Pediatrics Age Estimation: An Empirical Testing Perspective using Medical Images
Keywords:
Bone age assessment, pediatric radiographs, CNN–GAN hybrid, ossification and fusion, AI testing framework, medical image analysis.Abstract
Accurate pediatric age estimation is essential for diagnosing growth disorders and developmentalabnormalities. Conventional atlas-based methods such as Greulich–Pyle and Tanner–Whitehouse armanual, time-consuming, and subject to inter-observer variability, especially across diverse populations. This study presents an empirical evaluation
References
H. Lee et al., “Fully automated deep learning system for bone age assessment,” IEEE Trans. Med. Imaging, vol. 39, no. 10, pp. 3250–3261, 2020.
Y. Li et al., “Bone age recognition using Mask R-CNN and Xception,” Biomed. Signal Process. Control, vol. 57, 2020.
Downloads
Published
2024-09-25
How to Cite
Rumana Anjum, Madhu B K. (2024). Ensuring Accuracy in AI-Based Pediatrics Age Estimation: An Empirical Testing Perspective using Medical Images. Journal of Computational Analysis and Applications (JoCAAA), 33(06), 3913–3921. Retrieved from https://www.eudoxuspress.com/index.php/pub/article/view/4858
Issue
Section
Articles
