Artificial Intelligence in Orthopedic Image Analysis: A Systematic Review and Unified Taxonomy of Bone Age Assessment and Fracture Detection.
Authors
Affiliations (5)
Affiliations (5)
- Health Informatics Research Lab, Department of Computer Science and Engineering, Daffodil International University, Dhaka, 1216, Bangladesh.
- Health Informatics Research Lab, Department of Computer Science and Engineering, Daffodil International University, Dhaka, 1216, Bangladesh. [email protected].
- Department of Orthopedics, Dhaka Medical College and Hospital, Dhaka, 1000, Bangladesh.
- Department of Information and Communication Engineering, Yeungnam University, Gyeongsan, Republic of South Korea. [email protected].
- Department of Computer Science and Engineering, United International University, Dhaka, 1212, Bangladesh.
Abstract
Bone age assessment (BAA) and fracture detection are essential tasks in orthopedic radiography, since they aid diagnosis and clinical decision-making in trauma treatment. Recent technologies in artificial intelligence (AI), particularly deep learning (DL), have enhanced the ability to analyze radiological images with greater accuracy and consistency. However, current studies are incomplete, with inconsistent evaluation methodologies, limited external validation, and insufficient interpretability, limiting clinical implementation. This study provides a systematic PRISMA-based review of 116 studies (2017-2025) that analyze imaging modalities, datasets, model architectures, evaluation techniques, and clinical relevance. A uniform taxonomy is introduced to define techniques based on task, modality, and learning paradigm, along with a comparative methodology to address inconsistencies across studies. The findings indicate that CNN and transformer-based models achieve MAE as low as 0.4-0.7 years and accuracy exceeding 95% in controlled datasets but are limited by dataset bias, poor generalization, and a lack of standardized benchmarks. Although explainable AI (XAI) approaches increase interpretability, their clinical reliability is still limited. This review synthesizes current methodologies, identifies key problems, and proposes future directions for AI systems that are robust, interpretable, and clinically deployable, while unifying BAA and fracture detection under a single taxonomy that integrates modality, task, and learning paradigm.