Automated Pediatric Bone Age Prediction Using Multitask Deep Learning Techniques
International Journal of Drug Delivery Technology · 14.05.2026 · 16 (34s)
DOI: 10.25258/ijddt.16.34s.89 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 14.05.2026. Verfasst von Rumana Anjum und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Bone age assessment is an important diagnostic tool in pediatric medicine to determine growth and developmental disorders. The proposed research project introduces a deep learning-driven, multitask, clinically reliable automated model to estimate the age of children's bones. The model combines both classification and regression into an EfficientNetB4-based framework to forecast developmental stages and accurately determine bone age. A structured preprocessing pipeline and a gender-based input representation are also introduced to enhance feature extraction. Also, there is a six-layer validation framework and a three-layer safety mechanism to guarantee the quality of input and quality predictions. Another aspect that is introduced in the system is the confidence estimation module that will be used in the process of clinical decision-making. Trained on the RSNA pediatric dataset, the model has a competitive performance with the ability to be interpreted and robust. The proposed model is clinical usability-oriented, safety-oriented, and deployment-ready, unlike the traditional and regression-only models. Overall, the research provides a solution that is scalable and interpretable and can bridge the gap between the artificial intelligence models and the reality of the field of pediatric healthcare.
Zitieren
APA
Anjum, R., K, D. M. B., & Anjum, D. R. (2026). Automated Pediatric Bone Age Prediction Using Multitask Deep Learning Techniques. International Journal of Drug Delivery Technology, 16(34s). https://doi.org/10.25258/ijddt.16.34s.89
Vancouver
Anjum R, K DMB, Anjum DR. Automated Pediatric Bone Age Prediction Using Multitask Deep Learning Techniques. International Journal of Drug Delivery Technology. 2026;16(34s). doi:10.25258/ijddt.16.34s.89
BibTeX
@article{Anjum2026,
author = {Anjum, Rumana and K, Dr. Madhu B and Anjum, Dr. Reshma},
title = {Automated Pediatric Bone Age Prediction Using Multitask Deep Learning Techniques},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {34s},
doi = {10.25258/ijddt.16.34s.89}
}
EUVIMED