EUVIMEDEUVIMED entdecken
Crossref

EVAD-YOLO: An endoscopic video anomaly detection based on improved YOLOV11

Minghan Dong, Xia Zhang, Xiangwei Zheng, Mingzhe Zhang

Medical & Biological Engineering & Computing · 2026

DOI: 10.1007/s11517-026-03532-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, 2026. Verfasst von Minghan Dong und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Artificial Intelligence, Shandong Normal University, Jinan, 250358, China. Hauptthemen laut MEDLINE: Video Recording, Endoscopy, Gastrointestinal, Image Processing, Computer-Assisted. Die Arbeit nennt 40 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, automated analysis of gastrointestinal endoscopy videos has become increasingly important for early clinical screening as the incidence of gastrointestinal diseases continues to increase. However, the complex characteristics of gastrointestinal lesions pose significant challenges for accurate identification and diagnosis. This paper proposes an Endoscopic Video Anomaly Detection based on improved YOLOV11(EVAD-YOLO) for detecting typical lesions such as gastric ulcers and gastric cancer. Specifically, we construct a Residual global expansion attention (RGEA) module to enhance global contextual perception and improve sensitivity to lesions with complex shapes and color variations. In addition, we design an Enhanced multi-scale fusion (EMSF) module to effectively integrate lesion features across different spatial scales, thereby improving detection robustness for lesions of varying sizes. Furthermore, we built a mixed endoscopic dataset containing polyps, gastric ulcers, and early gastric cancers to comprehensively evaluate the proposed method. Experimental results demonstrate that EVAD-YOLO achieves superior performance, with 90.4% precision, 84.3% recall, and 90.4 % mAP50, indicating its strong robustness and potential for reliable clinical-assisted endoscopic diagnosis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Video RecordingEndoscopy, GastrointestinalImage Processing, Computer-AssistedHumansDetection AlgorithmsStomach NeoplasmsAlgorithms

Stichwörter der Autor:innen

Anomaly DetectionAttention MechanismMultiscale FusionYOLO

Autor:innen und Institutionen

  • School of Computer Science and Artificial Intelligence, Shandong Normal University, Jinan, 250358, China.
  • Internet Diagnosis and Treatment Center, Taian City Central Hospital, Taian, 271000, China.
  • School of Computer Science and Artificial Intelligence, Shandong Normal University, Jinan, 250358, China. xwzhengcn@163.com.

Zitieren

APA

Dong, M., Zhang, X., Zheng, X., & Zhang, M. (2026). EVAD-YOLO: An endoscopic video anomaly detection based on improved YOLOV11. Medical & Biological Engineering & Computing. https://doi.org/10.1007/s11517-026-03532-0

Vancouver

Dong M, Zhang X, Zheng X, Zhang M. EVAD-YOLO: An endoscopic video anomaly detection based on improved YOLOV11. Medical & Biological Engineering & Computing. 2026. doi:10.1007/s11517-026-03532-0

BibTeX
@article{Dong2026,
  author = {Dong, Minghan and Zhang, Xia and Zheng, Xiangwei and Zhang, Mingzhe},
  title = {EVAD-YOLO: An endoscopic video anomaly detection based on improved YOLOV11},
  journal = {Medical & Biological Engineering & Computing},
  year = {2026},
  doi = {10.1007/s11517-026-03532-0}
}
Kostenlos starten →