lnu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Small Data, Big Impact: A Multi-Locale Bone Fracture Detection on an Extremely Limited Dataset Via Crack-Informed YOLOv9 Variants
Norwegian University of Science and Technology, Norway.
Sukkur IBA University, Pakistan.
Norwegian University of Science and Technology, Norway.
Linnaeus University, Faculty of Technology, Department of Informatics. Linnaeus University, Linnaeus Knowledge Environments, Digital Transformations.ORCID iD: 0000-0002-0199-2377
Show others and affiliations
2024 (English)In: 2024 International Conference on Frontiers of Information Technology (FIT), IEEE, 2024Conference paper, Published paper (Refereed)
Abstract [en]

Automated wrist fracture recognition has becomea crucial research area due to the challenge of accurate X-ray interpretation in clinical settings without specialized expertise. With the development of neural networks, YOLO models have been extensively applied to fracture detection recently. However, detection models can struggle when trained on small datasets, which is often the case in medical scenarios. In this study, we utilize an extremely small multi-region fracture dataset and hypothesize that the structural similarities between surface cracks and bone fractures can allow YOLOv9 with a generalized efficient layer and programmable gradient information control to transfer knowledge effectively. We show that pre-training YOLOv9 on surface cracks rather than on COCO, which is how YOLO models are typically pre-trained, and fine-tuning it on the fracture dataset yields substantial performance improvements. We also show that knowledge gained from the surface cracks requires fewer epochs to converge and minimizes overfitting. We achieved state-of-the-art (SOTA) performance on the newly released FracAtlas dataset, surpassing the previously established benchmark. Our approach improved the mean average precision (mAP) score by 7% and sensitivity by 13%.

Place, publisher, year, edition, pages
IEEE, 2024.
Keywords [en]
Fracture detection, Medical x-ray imaging, Trans- fer learning, YOLOv9, Object detection
National Category
Medical Engineering Computer Sciences
Research subject
Computer and Information Sciences Computer Science, Computer Science
Identifiers
URN: urn:nbn:se:lnu:diva-134644DOI: 10.1109/FIT63703.2024.10838409Scopus ID: 2-s2.0-85217394008OAI: oai:DiVA.org:lnu-134644DiVA, id: diva2:1928946
Conference
2024 International Conference on Frontiers of Information Technology (FIT)
Available from: 2025-01-18 Created: 2025-01-18 Last updated: 2025-03-05Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Kastrati, Zenun

Search in DiVA

By author/editor
Kastrati, Zenun
By organisation
Department of InformaticsDigital Transformations
Medical EngineeringComputer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 84 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf