EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PEYOLO: a wrist fracture detection network based on multi-level receptive field feature extraction and cross-scale fusion

Shuwei Zhang, Rong Tang, Jiong Mu, Shaohai Ren

Frontiers in Medicine · 11.05.2026 · 13

DOI: 10.3389/fmed.2026.1850116 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Medicine, online erschienen am 11.05.2026. Verfasst von Shuwei Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Orthopedic Department, Handan First Hospital, Handan, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

The wrist is a high-incidence site for traumatic injuries in the skeletal system, where rapid and accurate diagnosis of fractures is critically important in clinical practice. However, the complex multi-scale variations of fractures impede precise detection of wrist fractures.

Methods

To address this issue, this study proposes a novel wrist fracture detection model, PEYOLO, based on multi-level receptive field feature extraction and cross-scale feature fusion. First, we design a Parallel Dilated Multi-head Attention Module (PDMAM), which performs sparse sampling under different receptive fields to simultaneously obtain receptive fields of varying scales within the same layer. Second, we introduce an Efficient Multi-Scale Attention module, which enhances the perception of multi-scale fracture features by fusing multi-scale spatial information with cross-dimensional dependencies.

Results

Experimental results on the GRAZPEDWRI-DX-fracture dataset demonstrate that PEYOLO improves mAP by 1.4% over the baseline and outperforms several state-of-the-art object detection models.

Discussion

PEYOLO has demonstrated highly advantageous high precision and inference speed, making it an important tool for clinical diagnosis and treatment planning.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismdeep learningmulti-scaleobject detectionwrist fracture

Autor:innen und Institutionen

  • Orthopedic Department, Handan First Hospital, Handan, China.
  • Graduate School, Chengde Medical College, Chengde, China.
  • College of Information Engineering, Sichuan Agricultural University, Ya'an, China.

Zitieren

APA

Zhang, S., Tang, R., Mu, J., & Ren, S. (2026). PEYOLO: a wrist fracture detection network based on multi-level receptive field feature extraction and cross-scale fusion. Frontiers in Medicine, 13. https://doi.org/10.3389/fmed.2026.1850116

Vancouver

Zhang S, Tang R, Mu J, Ren S. PEYOLO: a wrist fracture detection network based on multi-level receptive field feature extraction and cross-scale fusion. Frontiers in Medicine. 2026;13. doi:10.3389/fmed.2026.1850116

BibTeX
@article{Zhang2026,
  author = {Zhang, Shuwei and Tang, Rong and Mu, Jiong and Ren, Shaohai},
  title = {PEYOLO: a wrist fracture detection network based on multi-level receptive field feature extraction and cross-scale fusion},
  journal = {Frontiers in Medicine},
  year = {2026},
  volume = {13},
  doi = {10.3389/fmed.2026.1850116}
}
Kostenlos starten →