Anatomical Alignment of Femoral Radiographs Enables Robust AI-Powered Detection of Incomplete Atypical Femoral Fractures

Doyoung Kwon, Jin-Han Lee, Joon-Woo Kim, Ji-Wan Kim, Sun-jung Yoon, Sungmoon Jeong () and Chang-Wug Oh ()
Additional contact information
Doyoung Kwon: School of Artificial Intelligence, Kyungpook National University, Daegu 41566, Republic of Korea
Jin-Han Lee: Department of Orthopedic Surgery, School of Medicine, Kyungpook National University Hospital, Kyungpook National University, Daegu 07364, Republic of Korea
Joon-Woo Kim: Department of Orthopedic Surgery, School of Medicine, Kyungpook National University Hospital, Kyungpook National University, Daegu 07364, Republic of Korea
Ji-Wan Kim: Department of Orthopaedic Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul 05505, Republic of Korea
Sun-jung Yoon: Department of Orthopedic Surgery, Jeonbuk National University Medical School, Jeonju 54907, Republic of Korea
Sungmoon Jeong: Department of Medical Informatics, Kyungpook National University, Daegu 41566, Republic of Korea
Chang-Wug Oh: Department of Orthopedic Surgery, School of Medicine, Kyungpook National University Hospital, Kyungpook National University, Daegu 07364, Republic of Korea

Mathematics, 2025, vol. 13, issue 22, 1-23

Abstract: An Incomplete Atypical femoral fracture is subtle and requires early diagnosis. However, artificial intelligence models for these fractures often fail in real-world clinical settings due to the “domain shift” problem, where performance degrades when applied to new data sources. This study proposes a data-centric approach to overcome this problem. We introduce an anatomy-based four-step preprocessing pipeline to normalize femoral X-ray images. This pipeline consists of (1) semantic segmentation of the femur, (2) skeletonization and centroid extraction using RANSAC, (3) rotational alignment to the vertical direction, and (4) cropping a normalized region of interest (ROI). We evaluate the effectiveness of this pipeline across various one-stage (YOLO) and two-stage (Faster R-CNN) object detection models. On the source domain data, the proposed alignment pipeline significantly improves the performance of the YOLO model, with YOLOv10n achieving the best performance of 0.6472 at mAP@50–95. More importantly, in zero-shot evaluation on a completely new domain, standing AP X-ray, the model trained on aligned data exhibited strong generalization performance, while the existing models completely failed (mAP = 0), YOLOv10s, which applied the proposed method, achieved 0.4616 at mAP@50–95. The first-stage detector showed more consistent performance gains from the alignment technique than the second-stage detector. Normalizing medical images based on inherent anatomical consistency is a highly effective and efficient strategy for achieving domain generalization. This data-driven paradigm, which simplifies the input to AI, can create clinically applicable, robust models without increasing the complexity of the model architecture.

Keywords: incomplete atypical femoral fracture; domain generalization; data-centric AI; object detection; X-ray (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/22/3720/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/22/3720/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:22:p:3720-:d:1798876

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().