A Systematic Analysis of Input Modalities for Fracture Classification of the Paediatric Wrist
This work addresses fracture classification for children and adolescents, an incremental improvement over existing deep learning methods by exploring underutilized modalities.
The paper tackled the problem of classifying pediatric wrist fractures by systematically analyzing the impact of incorporating additional input modalities beyond radiographs, such as automatic bone segmentation, fracture location, and radiology reports, resulting in an increase in AUROC from 91.71 to 93.25.
Fractures, particularly in the distal forearm, are among the most common injuries in children and adolescents, with approximately 800 000 cases treated annually in Germany. The AO/OTA system provides a structured fracture type classification, which serves as the foundation for treatment decisions. Although accurately classifying fractures can be challenging, current deep learning models have demonstrated performance comparable to that of experienced radiologists. While most existing approaches rely solely on radiographs, the potential impact of incorporating other additional modalities, such as automatic bone segmentation, fracture location, and radiology reports, remains underexplored. In this work, we systematically analyse the contribution of these three additional information types, finding that combining them with radiographs increases the AUROC from 91.71 to 93.25. Our code is available on GitHub.