EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

YOLOv7‐RepFPN: Improving real‐time performance of laparoscopic tool detection on embedded systems

Yuzhang Liu iD, Yuichiro Hayashi, Masahiro Oda, Takayuki Kitasaka, Kensaku Mori

Healthcare Technology Letters · 2024-04 · 11 (2-3) · 157-166

DOI: 10.1049/htl2.12072 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Healthcare Technology Letters, online erschienen am 23.01.2024. Verfasst von Yuzhang Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Informatics Nagoya University Aichi, Nagoya Japan. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study focuses on enhancing the inference speed of laparoscopic tool detection on embedded devices. Laparoscopy, a minimally invasive surgery technique, markedly reduces patient recovery times and postoperative complications. Real‐time laparoscopic tool detection helps assisting laparoscopy by providing information for surgical navigation, and its implementation on embedded devices is gaining interest due to the portability, network independence and scalability of the devices. However, embedded devices often face computation resource limitations, potentially hindering inference speed. To mitigate this concern, the work introduces a two‐fold modification to the YOLOv7 model: the feature channels and integrate RepBlock is halved, yielding the YOLOv7‐RepFPN model. This configuration leads to a significant reduction in computational complexity. Additionally, the focal EIoU (efficient intersection of union) loss function is employed for bounding box regression. Experimental results on an embedded device demonstrate that for frame‐by‐frame laparoscopic tool detection, the proposed YOLOv7‐RepFPN achieved an mAP of 88.2% (with IoU set to 0.5) on a custom dataset based on EndoVis17, and an inference speed of 62.9 FPS. Contrasting with the original YOLOv7, which garnered an 89.3% mAP and 41.8 FPS under identical conditions, the methodology enhances the speed by 21.1 FPS while maintaining detection accuracy. This emphasizes the effectiveness of the work.

Schlagwörter

Stichwörter der Autor:innen

medical image processingobject detection

Autor:innen und Institutionen

  • Graduate School of Informatics Nagoya University Aichi, Nagoya Japan.
  • Information and Communications Nagoya University Aichi Nagoya Japan.
  • Department of Information Science Aichi Institute of Technology Aichi, Nagoya Japan.
  • Research Center of Medical Bigdata National Institute of Informatics Tokyo Japan.

ORCID-Profile: Yuzhang Liu

Zitieren

APA

Liu, Y., Hayashi, Y., Oda, M., Kitasaka, T., & Mori, K. (2024). YOLOv7‐RepFPN: Improving real‐time performance of laparoscopic tool detection on embedded systems. Healthcare Technology Letters, 11(2-3), 157-166. https://doi.org/10.1049/htl2.12072

Vancouver

Liu Y, Hayashi Y, Oda M, Kitasaka T, Mori K. YOLOv7‐RepFPN: Improving real‐time performance of laparoscopic tool detection on embedded systems. Healthcare Technology Letters. 2024;11(2-3):157-166. doi:10.1049/htl2.12072

BibTeX
@article{Liu2024,
  author = {Liu, Yuzhang and Hayashi, Yuichiro and Oda, Masahiro and Kitasaka, Takayuki and Mori, Kensaku},
  title = {YOLOv7‐RepFPN: Improving real‐time performance of laparoscopic tool detection on embedded systems},
  journal = {Healthcare Technology Letters},
  year = {2024},
  volume = {11},
  number = {2-3},
  pages = {157--166},
  doi = {10.1049/htl2.12072}
}
Kostenlos starten →