Lightweight YOLOv8 variants for enhanced real-time surgical tool detection
PeerJ Computer Science · 06.03.2026 · 12 · e3622
DOI: 10.7717/peerj-cs.3622 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 06.03.2026. Verfasst von Tuan Manh Do und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Vietnam National University, Hanoi.
Abstract (Originalsprache)
Accurate and real-time surgical tool detection is essential in minimally invasive surgery (MIS) to ensure safe and effective computer-assisted interventions (CAI) and robot-assisted surgery (RAS). However, achieving high accuracy under the strict computational constraints of embedded surgical platforms remains a significant challenge. This article introduces a set of enhanced lightweight You Only Look Once (YOLO)v8 variants specifically tailored for real-time surgical tool localization. The proposed architectures integrate several key innovations: Ghost Convolution for efficient feature extraction, a C2f-Ghost module for compact representation, and the SC3T module, which synergizes Transformer blocks with Spatial Pyramid Pooling. Additionally, attention mechanisms—including the Context Augmentation Module (CAM) and Convolutional Block Attention Module (CBAM)—are incorporated to refine feature discriminability. Furthermore, the Scylla-Intersection over Union (SIoU) loss is employed to optimize bounding box regression for elongated instruments. Evaluations on the public m2cai16-tool-locations dataset demonstrate that the best variant achieves 95.7% mAP@0.5 while reducing parameters and Giga FLOating-point Operation(s) Per Seconds (GFLOPs) by up to 3× and 1.8×, respectively, compared to the YOLOv8 baseline. These results indicate that our design offers a competitive accuracy-efficiency trade-off, facilitating practical deployment in resource-constrained, real-time surgical systems.
Förderung
- Vietnam National University, Hanoi
Zitieren
APA
Do, T. M., Kim, T. D., & Le, H. X. (2026). Lightweight YOLOv8 variants for enhanced real-time surgical tool detection. PeerJ Computer Science, 12, e3622. https://doi.org/10.7717/peerj-cs.3622
Vancouver
Do TM, Kim TD, Le HX. Lightweight YOLOv8 variants for enhanced real-time surgical tool detection. PeerJ Computer Science. 2026;12:e3622. doi:10.7717/peerj-cs.3622
BibTeX
@article{Do2026,
author = {Do, Tuan Manh and Kim, Thai Dinh and Le, Hai Xuan},
title = {Lightweight YOLOv8 variants for enhanced real-time surgical tool detection},
journal = {PeerJ Computer Science},
year = {2026},
volume = {12},
pages = {e3622},
doi = {10.7717/peerj-cs.3622}
}
EUVIMED